© 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. 161364
    Prev
    Next
    INDEX
    Explanations

    path to or method

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

    class, constructor, params, medium, safety, forest

    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
    يا
    0.50
     nuisance
    0.49
    转
    0.46
    걸
    0.46
     sector
    0.45
    왑
    0.44
     skirt
    0.44
     skirts
    0.44
    洒
    0.44
    ర్‌
    0.43
    POSITIVE LOGITS
     умови
    0.52
    mathb
    0.51
    paren
    0.49
    that
    0.46
    ObjectType
    0.46
    ymers
    0.45
    mails
    0.44
    mortar
    0.44
    hardt
    0.44
    forceable
    0.43
    Activations Density 0.000%

    No Known Activations