© 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. 68699
    Prev
    Next
    INDEX
    Explanations

    iframe and webview tags

    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
    Negative Logits
    '
    -1.94
     Schluß
    -1.60
    瓩
    -1.55
     cheia
    -1.48
    flasche
    -1.47
    棡
    -1.44
    st
    -1.43
    ningarna
    -1.42
     Gefühle
    -1.41
     tentando
    -1.41
    POSITIVE LOGITS
     BOTH
    2.05
    mmm
    1.65
    u
    1.62
    ización
    1.52
    émie
    1.52
    ://
    1.50
     והוא
    1.49
    beitung
    1.47
    ícias
    1.45
    ckeye
    1.45
    Activations Density 0.019%

    No Known Activations