© 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. 98960
    Prev
    Next
    INDEX
    Explanations

    asking for information

    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
    </b>
    -2.08
     It
    -2.05
     urge
    -2.02
     喜欢
    -1.95
     savvy
    -1.93
    );
    -1.91
     avec
    -1.77
     bilden
    -1.77
     say
    -1.75
     希望
    -1.75
    POSITIVE LOGITS
    哢
    2.27
    ments
    1.98
     about
    1.96
    led
    1.95
    ids
    1.85
    اته
    1.80
    麈
    1.77
    XICO
    1.76
    先は
    1.75
    there
    1.73
    Activations Density 0.007%

    No Known Activations