© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6697
    Prev
    Next
    INDEX
    Explanations

    </MAX_ACTIVATING_TOKENS>8331200042</MAX_ACTIVATING_TOKENS><TOKENS_AFTER_MAX_ACTIVATING_TOKEN>ff454)7)"2,</TOKENS_AFTER_MAX_ACTIVATING_TOKEN><TOP_POSITIVE_LOGITS>).”inforclaimedwanted),”wentandto.”</TOP_POSITIVE_LOGITS><TOP_ACTIVATING_TEXTS>the highest mountains, and was also claimed to be the highest mountain in Africa. Mount Kilimanjaro is a dormant volcanoto be the highest mountain in Africa. Mount Kilimanjaro is a dormant volcano. The tallest mountain in the world is Everestthe highest mountain in Africa. Mount Kilimanjaro is a dormant volcano. The tallest mountain in the world is Everestto be the tallest mountain in Africa. Mount Kilimanjaro is a dormant volcano. The tallest mountain in the world is Everestclaimed to be the highest mountain in Africa. Mount Kilimanjaro is a dormant volcano. The tallest mountain in the world is Everest"most of the people wanted to know whether he decided to kill himself. The day he went home, he sat on hismost of the people wanted to know whether he decided to kill himself. The day he went home, he sat on his chairmost of my people wanted to know whether he decided to kill himself. The day he went home, he sat on hismost of the people wanted to know whether he decided to kill himself. The day he went home, he sat on hismost of the people wanted to know whether he decided to kill himself. The day he went home, he sat on his chair.</TOP_ACTIVATING_TEXTS>Explain the neuron above with a word or phrase, not a complete sentence.claimed to be the highest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    6
    1.69
    '
    1.63
    4
    1.61
    2
    1.58
    3
    1.56
    0
    1.53
    .
    1.48
    7
    1.48
    9
    1.48
    1
    1.45
    POSITIVE LOGITS
    ).”
    1.48
     in
    1.39
     for
    1.37
    ছেন
    1.35
    㳑
    1.30
    ),”
    1.30
    㗽
    1.27
    →</
    1.22
     and
    1.20
    ].”
    1.19
    Activations Density 0.400%

    No Known Activations