© 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. 127965
    Prev
    Next
    INDEX
    Explanations

    same thing, would all, making sure

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

    come from, even, focused on

    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
    واری
    0.55
    ب
    0.54
    مع
    0.50
    اي
    0.50
     wholly
    0.49
     drawbacks
    0.48
    வக
    0.47
    ن
    0.46
    respective
    0.46
    انو
    0.46
    POSITIVE LOGITS
     Đế
    0.51
     पाठक
    0.48
     Beding
    0.44
     благодаря
    0.44
    蛩
    0.44
    MCs
    0.43
     Rett
    0.43
    比赛
    0.43
     dzięki
    0.43
     Dop
    0.43
    Activations Density 0.000%

    No Known Activations