© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 18
    Prev
    Next
    INDEX
    Explanations

    game records

    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
    最終
    -1.10
    最後
    -1.05
     endgül
    -1.02
    最终
    -1.00
    kün
    -0.95
     akhir
    -0.94
     cena
    -0.94
    FINAL
    -0.93
     pesce
    -0.93
     finale
    -0.92
    POSITIVE LOGITS
     early
    1.18
     zatím
    1.05
    Early
    0.96
     Early
    0.96
    {(-
    0.91
     debut
    0.91
     preseason
    0.90
     hned
    0.86
     TRENDS
    0.86
     menu
    0.85
    Activations Density 0.041%

    No Known Activations