© 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. 34-GEMMASCOPE-RES-131K
    7. 29922
    Prev
    Next
    INDEX
    Explanations

    Q: followed by code or technical question

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     يكن
    -0.95
    ropshire
    -0.82
    举例
    -0.79
     vulture
    -0.73
    elding
    -0.72
    Mitochond
    -0.71
     quoque
    -0.71
    InteropServices
    -0.70
    =\
    -0.68
    حد
    -0.68
    POSITIVE LOGITS
     svg
    1.28
    svg
    1.25
     CHART
    1.00
     Virginia
    1.00
     SVG
    0.97
    SVG
    0.97
    Virginia
    0.93
     dragen
    0.92
    vega
    0.92
    Vega
    0.88
    Activations Density 0.044%

    No Known Activations