© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20902
    Prev
    Next
    INDEX
    Explanations

    State University

    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_10/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
    ୩
    -1.95
    躂
    -1.93
     связанные
    -1.92
    敉
    -1.73
    生活的
    -1.65
    䊐
    -1.64
    isées
    -1.63
    ti
    -1.63
     sogenannte
    -1.62
    铙
    -1.62
    POSITIVE LOGITS
    ဴ
    1.68
    .”
    1.66
    隰
    1.55
     Bezeichnung
    1.54
    '
    1.52
    呔
    1.52
     Berechnung
    1.51
     escuro
    1.51
     emphasis
    1.50
    而又
    1.49
    Activations Density 0.005%

    No Known Activations