© 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. 60421
    Prev
    Next
    INDEX
    Explanations

    LaTeX package commands

    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
    🤢
    -2.05
     and
    -2.03
    🤨
    -1.89
    🧐
    -1.84
    🥴
    -1.79
    🥶
    -1.79
    省市镇
    -1.77
    🥱
    -1.74
    ZIONE
    -1.73
    皷
    -1.69
    POSITIVE LOGITS
    さすが
    1.92
    というわけで
    1.85
    ing
    1.82
    にほんブログ村
    1.79
    さてさて
    1.78
    なるほど
    1.73
     $
    1.71
    たしか
    1.70
     sorta
    1.68
    about
    1.64
    Activations Density 0.012%

    No Known Activations