© 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. 32201
    Prev
    Next
    INDEX
    Explanations

    each of

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

    individual items or categories

    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
    $
    0.90
    Ց
    0.81
     américains
    0.80
    𝑻
    0.79
     settembre
    0.75
     altında
    0.73
    houses
    0.73
     eyelashes
    0.72
    𝗦
    0.71
    ᱖
    0.71
    POSITIVE LOGITS
    د
    1.08
    с
    1.00
    ور
    0.99
    те
    0.96
    в
    0.94
    ก
    0.93
     of
    0.92
    от
    0.91
    were
    0.90
    у
    0.89
    Activations Density 0.064%

    No Known Activations