© 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. 64510
    Prev
    Next
    INDEX
    Explanations

    dates, times, and numbers

    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
    -0.90
     ilust
    -0.87
     atyp
    -0.86
     reklama
    -0.85
     mestre
    -0.85
     variantes
    -0.85
     espada
    -0.84
     maître
    -0.84
     éclair
    -0.83
    kenal
    -0.83
    POSITIVE LOGITS
    ściej
    0.97
     freue
    0.94
    重要的是
    0.93
     tätig
    0.92
    闌
    0.90
    n
    0.88
     storey
    0.88
    ädig
    0.85
    Выводы
    0.85
     augusti
    0.84
    Activations Density 0.002%

    No Known Activations