© 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. 24906
    Prev
    Next
    INDEX
    Explanations

    legal citations and years

    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
     między
    -0.75
     fidget
    -0.73
    CRIP
    -0.71
     иначе
    -0.70
    утбо
    -0.69
    有一些
    -0.68
    biele
    -0.68
     evitar
    -0.68
     algumas
    -0.68
     Zep
    -0.68
    POSITIVE LOGITS
    due
    1.10
     due
    1.09
    Berdasarkan
    0.95
    Due
    0.94
     λό
    0.92
    depending
    0.88
     even
    0.88
     súčas
    0.87
     Aufgrund
    0.86
     depending
    0.85
    Activations Density 0.004%

    No Known Activations