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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 641
    Prev
    Next
    INDEX
    Explanations

    (Nubia, domestic cats, according to, developing, trying, zero-shot)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_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
    อย่าง
    0.25
    и
    0.23
     powerAll
    0.22
    ständig
    0.22
    ों
    0.22
     immobil
    0.22
     scheduler
    0.22
    х
    0.21
    ς
    0.21
     சார்ந்த
    0.21
    POSITIVE LOGITS
    \
    0.29
    {
    0.27
    in
    0.27
    K
    0.27
    গ
    0.26
    D
    0.25
    H
    0.23
    }
    0.23
    }\
    0.23
    iszt
    0.23
    Activations Density 0.166%

    No Known Activations