© 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. 6747
    Prev
    Next
    INDEX
    Explanations

    code prefixes like `(` or `//`

    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
    蛲
    -1.91
     插画
    -1.87
    垰
    -1.80
    鹀
    -1.76
     mantém
    -1.75
    苤
    -1.73
     această
    -1.71
    eſ
    -1.70
    were
    -1.69
     imó
    -1.69
    POSITIVE LOGITS
     like
    1.70
     as
    1.55
     for
    1.54
    D
    1.45
     using
    1.44
     from
    1.42
    //
    1.41
    ;
    1.33
    dė
    1.29
     roaming
    1.28
    Activations Density 0.012%

    No Known Activations