© 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. 89732
    Prev
    Next
    INDEX
    Explanations

    word endings like k, ck, or phonemes like ark, malk

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

    plakortolides, Piskel, cockatrice

    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
     you
    1.01
    f
    1.00
    you
    0.91
    t
    0.88
    <0x80>
    0.84
    ong
    0.79
    ar
    0.77
    ad
    0.75
    n
    0.75
    A
    0.74
    POSITIVE LOGITS
    к
    1.18
    м
    1.04
    ه
    0.91
    من
    0.89
    ни
    0.88
    ك
    0.88
    το
    0.86
    steins
    0.85
     on
    0.84
    ड
    0.82
    Activations Density 2.224%

    No Known Activations