© 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. 67016
    Prev
    Next
    INDEX
    Explanations

    & followed by continuations

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

    tech abbreviation followed by concept

    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
    ви
    0.68
    _
    0.65
     alanı
    0.59
    或者
    0.57
    Телефон
    0.55
    這個
    0.54
    ा
    0.53
    ǜ
    0.52
    ారం
    0.52
    (
    0.52
    POSITIVE LOGITS
     meski
    0.77
     prepd
    0.71
     yrs
    0.65
    ك
    0.63
    govt
    0.63
     σε
    0.62
     Hwy
    0.62
     समेत
    0.61
     соц
    0.61
     Dems
    0.61
    Activations Density 0.778%

    No Known Activations