© 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. 32891
    Prev
    Next
    INDEX
    Explanations

    data structures and organization

    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
    Not in Any Lists

    No Comments

    Negative Logits
    strSql
    -1.02
    +"_
    -0.96
     tucson
    -0.94
    ('+
    -0.89
    ровании
    -0.88
     '|
    -0.88
    reurs
    -0.86
    溴
    -0.86
    ANTS
    -0.85
     mignon
    -0.85
    POSITIVE LOGITS
     it
    1.05
    AutoModerator
    1.00
    muebles
    0.98
     seguirá
    0.94
     its
    0.94
     eighth
    0.91
     llevaron
    0.91
     mundiales
    0.90
    dentro
    0.90
     paroisse
    0.90
    Activations Density 0.195%

    No Known Activations