© 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. 22-GEMMASCOPE-RES-131K
    7. 32787
    Prev
    Next
    INDEX
    Explanations

    located

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Drž
    -1.38
     konkre
    -1.15
     disparu
    -1.14
     unicórnio
    -1.13
     solchen
    -1.12
    jshint
    -1.10
     Projektu
    -1.09
     this
    -1.09
     сьогодні
    -1.08
     цьому
    -1.07
    POSITIVE LOGITS
    {?>
    1.22
     doesn
    1.19
     is
    1.13
    w
    1.12
    will
    1.12
    ueves
    1.05
    方針
    1.05
    igation
    1.04
     didn
    1.04
    usted
    1.03
    Activations Density 0.244%

    No Known Activations