© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41648
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by common short words

    np_acts-logits-general · gemini-2.5-flash-lite

    special characters forming lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ال
    0.89
    ни
    0.88
     كه
    0.81
    S
    0.77
     (
    0.76
    К
    0.76
     at
    0.75
     that
    0.74
     of
    0.73
    الك
    0.73
    POSITIVE LOGITS
    as
    0.91
    ę
    0.87
     dined
    0.82
    ó
    0.77
    es
    0.77
    بلی
    0.77
    ä
    0.77
    ang
    0.76
    ie
    0.73
    ą
    0.73
    Activations Density 0.157%

    No Known Activations