© 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. 68580
    Prev
    Next
    INDEX
    Explanations

    system capabilities

    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
    猡
    -2.31
    蚍
    -2.31
    鸱
    -2.25
     pérd
    -2.23
    妧
    -2.20
    鷸
    -2.19
    臏
    -2.17
    蟊
    -2.17
    
    -2.17
    嗵
    -2.17
    POSITIVE LOGITS
    ↵↵
    2.75
     l
    2.52
    {
    2.36
    [
    2.11
     However
    2.11
     It
    2.09
     to
    2.03
     entsprechenden
    1.96
     Können
    1.89
     of
    1.85
    Activations Density 0.057%

    No Known Activations