© 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. 142198
    Prev
    Next
    INDEX
    Explanations

    information quantity bill select

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

    interpret the law

    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
     वृत्त
    0.47
     Akbar
    0.46
    urado
    0.45
     firmado
    0.45
    边
    0.44
    顶点
    0.43
    ностях
    0.42
     impulso
    0.42
     cercle
    0.42
    닌
    0.42
    POSITIVE LOGITS
    ↵↵↵
    0.51
    <h1>
    0.48
    Alle
    0.46
    SELECT
    0.45
     SUPPL
    0.45
    ö
    0.44
    ç
    0.44
    <unused60>
    0.44
    Select
    0.44
    VI
    0.44
    Activations Density 0.000%

    No Known Activations