© 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. 71997
    Prev
    Next
    INDEX
    Explanations

    words after closing parentheses

    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
    nimmt
    -1.78
     Zijn
    -1.70
    zelfde
    -1.70
     voetballer
    -1.65
     Daarna
    -1.63
    ifié
    -1.63
     zijne
    -1.63
     fű
    -1.62
     Daarnaast
    -1.57
     shotguns
    -1.56
    POSITIVE LOGITS
    *
    2.13
    [
    1.84
    ly
    1.76
    re
    1.73
    '
    1.63
    ・・・・・
    1.61
    在你
    1.58
    ed
    1.53
     ένα
    1.52
    ’
    1.50
    Activations Density 0.025%

    No Known Activations