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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112910
    Prev
    Next
    INDEX
    Explanations

    antibody

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

    This neuron detects mentions of antibodies, particularly in immunological or medical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    )
    -3.63
    of
    -3.14
    (
    -2.91
    ."
    -2.63
    archiwizowane
    -2.59
    or
    -2.36
     של
    -2.25
    疣
    -2.22
     男孩
    -2.20
    on
    -2.19
    POSITIVE LOGITS
    '
    2.77
    梘
    2.73
    $
    2.67
    媖
    2.59
    --
    2.52
     ハロウィン
    2.48
     でも
    2.48
    椟
    2.44
    ()");
    2.42
    噚
    2.39
    Activations Density 0.016%

    No Known Activations