© 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. 9570
    Prev
    Next
    INDEX
    Explanations

    bounty hunter, Army Men, characters, Death, path, Industry

    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
     who
    -2.00
    苼
    -1.52
    癭
    -1.52
    糴
    -1.50
     then
    -1.48
    擽
    -1.48
    镡
    -1.46
     calorías
    -1.46
     потом
    -1.44
    然後
    -1.43
    POSITIVE LOGITS
     even
    2.39
     in
    2.14
     to
    1.91
     by
    1.84
     at
    1.82
     only
    1.73
     from
    1.71
     under
    1.59
    even
    1.56
    Even
    1.53
    Activations Density 0.095%

    No Known Activations