© 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. 181938
    Prev
    Next
    INDEX
    Explanations

    please visit, email, contact, submit

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

    please seek help

    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
    ;
    1.04
    r
    0.82
    :
    0.81
    larının
    0.77
    /
    0.75
    o
    0.74
    b
    0.65
    ri
    0.64
    ->
    0.63
    ;-
    0.62
    POSITIVE LOGITS
    اك
    0.78
    ע
    0.78
    на
    0.71
    U
    0.68
    éz
    0.67
    줘
    0.65
    ع
    0.62
    ти
    0.61
    ام
    0.61
    ви
    0.61
    Activations Density 0.019%

    No Known Activations