© 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. 100260
    Prev
    Next
    INDEX
    Explanations

    describing being hit or bitten

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    (
    -3.84
    \
    -3.81
    k
    -3.64
    j
    -3.31
    p
    -3.03
     humeur
    -2.75
    ar
    -2.75
    s
    -2.73
    ’
    -2.72
    z
    -2.69
    POSITIVE LOGITS
    也得
    2.95
    砹
    2.70
    だけではなく
    2.64
     They
    2.63
     conhecida
    2.52
    だけでなく
    2.50
     It
    2.48
     That
    2.45
     
    2.45
    盦
    2.42
    Activations Density 0.003%

    No Known Activations