© 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. 45022
    Prev
    Next
    INDEX
    Explanations

    how much one can

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

    you must

    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
     разум
    0.50
     एग्जांपल
    0.50
    盂
    0.50
     элементов
    0.49
     йөкләү
    0.47
     изменение
    0.47
    笏
    0.47
     मोटर्स
    0.46
     チェック
    0.45
     कॉपी
    0.45
    POSITIVE LOGITS
     or
    0.56
    three
    0.53
     three
    0.52
    [
    0.52
     and
    0.47
     trois
    0.47
     alternatives
    0.46
    (
    0.45
     substitutes
    0.44
     equivalent
    0.44
    Activations Density 0.001%

    No Known Activations