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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16090
    Prev
    Next
    INDEX
    Explanations

    win/loss records by season

    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
     an
    -0.98
     installation
    -0.96
     Micron
    -0.94
    THEOREM
    -0.93
    Preliminaries
    -0.93
    GONE
    -0.92
     equipment
    -0.91
     sprawie
    -0.89
     sufficient
    -0.89
     adequate
    -0.88
    POSITIVE LOGITS
     ultimi
    1.02
    icide
    1.02
     olika
    0.98
    ֠
    0.97
    𝖺
    0.97
    大事な
    0.95
    ਗ਼
    0.94
     abrir
    0.94
     بعد
    0.93
     Batal
    0.92
    Activations Density 0.015%

    No Known Activations