© 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. 25074
    Prev
    Next
    INDEX
    Explanations

    punctuation and foreign scripts

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

    sequence examples

    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
    ج
    0.91
    न
    0.83
    س
    0.83
    2
    0.81
    га
    0.72
    も
    0.72
     for
    0.71
    "
    0.69
    ق
    0.69
    ga
    0.68
    POSITIVE LOGITS
    τή
    0.73
    isinde
    0.71
    тно
    0.70
    то
    0.68
    تها
    0.64
    َف
    0.62
    üle
    0.60
    ันท
    0.58
    üyor
    0.57
    ты
    0.56
    Activations Density 0.088%

    No Known Activations