© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 113979
    Prev
    Next
    INDEX
    Explanations

    any, many, most

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

    automate tasks, scripts, and content

    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
    Negative Logits
    чает
    0.53
    ઋ
    0.52
    ってます
    0.49
    сное
    0.49
    теп
    0.45
     оплаты
    0.45
    тных
    0.45
    प्रयोग
    0.44
    았
    0.44
    ஷா
    0.44
    POSITIVE LOGITS
    p
    0.57
     New
    0.48
     decreasing
    0.47
    rc
    0.47
     on
    0.46
     English
    0.46
    c
    0.46
     with
    0.45
    rt
    0.45
     recent
    0.45
    Activations Density 0.000%

    No Known Activations