© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 3650
    Prev
    Next
    INDEX
    Explanations

    seroconversion or serves

    np_acts-logits-general · gemini-2.5-flash-lite

    names of people, particularly author names or bylines.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on capitalized proper names (entities) such as people or organizations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </strong>
    -2.39
     "
    -2.38
    ",
    -2.23
    .
    -2.17
     is
    -2.17
     I
    -2.13
     us
    -2.13
     heisst
    -2.11
     stronghold
    -2.05
     $
    -2.03
    POSITIVE LOGITS
     チラシ
    2.98
    錞
    2.89
    庒
    2.83
    ꯶
    2.80
    ＝＝＝＝
    2.69
    蹓
    2.58
    ◆◇
    2.58
    喁
    2.56
     撮っ
    2.55
    इटम
    2.47
    Activations Density 0.114%

    No Known Activations