© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 55497
    Prev
    Next
    INDEX
    Explanations

    principle, time, paddle, led, graft

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

    tone progression pattern

    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
    as
    0.43
     модель
    0.42
    avras
    0.42
     County
    0.41
     cifras
    0.41
    </strong>
    0.41
    বা
    0.41
     thụ
    0.41
     Statistics
    0.40
     breakouts
    0.39
    POSITIVE LOGITS
     أك
    0.45
    !"));
    0.44
    Вели
    0.44
    cesso
    0.42
    訴
    0.42
    !';
    0.42
    INGRE
    0.42
     समानता
    0.42
    ROY
    0.41
    $;
    0.41
    Activations Density 0.000%

    No Known Activations