© 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. 38677
    Prev
    Next
    INDEX
    Explanations

    skip hire

    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
     of
    -5.63
     it
    -2.09
     böyle
    -1.50
    :
    -1.48
    <bos>
    -1.48
    我就
    -1.41
     магази
    -1.37
     pirm
    -1.36
    ͑
    -1.33
     cette
    -1.31
    POSITIVE LOGITS
     motocicletas
    1.98
    七八
    1.80
     všechny
    1.80
     complementos
    1.76
    oció
    1.76
     bolsos
    1.75
     zosta
    1.73
     Stornier
    1.71
     кілька
    1.69
     decoracion
    1.67
    Activations Density 0.080%

    No Known Activations