© 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. 16403
    Prev
    Next
    INDEX
    Explanations

    measures and dimensions

    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
    鍇
    -1.04
     anivers
    -0.96
     vicini
    -0.94
     it
    -0.94
     variar
    -0.93
    jadas
    -0.93
    ⚙
    -0.91
     febbraio
    -0.91
     fotógrafo
    -0.91
     tett
    -0.90
    POSITIVE LOGITS
     максимально
    1.04
     vych
    1.03
     overly
    1.01
    さの
    1.00
     minimum
    0.98
     amount
    0.98
     max
    0.98
     دوب
    0.96
     promedio
    0.95
     anunció
    0.95
    Activations Density 0.003%

    No Known Activations