© 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. 8874
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and declarations

    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
    ﾚ
    -1.91
     unrelenting
    -1.86
    鹀
    -1.84
     promotes
    -1.82
     quoque
    -1.77
    前から
    -1.76
    های
    -1.72
    那個
    -1.70
     procesos
    -1.66
     jambe
    -1.66
    POSITIVE LOGITS
    ↵↵
    2.22
     I
    2.17
    ↵
    1.95
     decidedly
    1.88
    '
    1.84
    .
    1.82
     unn
    1.73
     elegantly
    1.72
     véritable
    1.68
     REALLY
    1.68
    Activations Density 0.003%

    No Known Activations