© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7024
    Prev
    Next
    INDEX
    Explanations

    __block, __kernel, __product__, __future__, __set__, __MT__, __LINUX__

    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
    us
    -2.03
    るので
    -1.83
    。”
    -1.79
     or
    -1.77
    ！”
    -1.77
     näm
    -1.72
    følgelig
    -1.72
     stessi
    -1.72
     frito
    -1.67
     because
    -1.63
    POSITIVE LOGITS
    <
    2.48
    [
    2.38
    ).
    2.30
    大好きな
    2.23
     was
    2.08
    ?
    2.02
    %;
    2.02
    (\
    1.90
    素晴らしい
    1.90
     gigantic
    1.89
    Activations Density 0.001%

    No Known Activations