© 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. 32487
    Prev
    Next
    INDEX
    Explanations

    app, critical, keep, No, out

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

    website code

    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
     살펴
    0.53
    媟
    0.47
     নৃত্য
    0.47
     vizsgál
    0.47
    谬
    0.46
     постепен
    0.46
     는
    0.46
     Đặc
    0.46
     setLayout
    0.46
    ёз
    0.46
    POSITIVE LOGITS
    ,
    0.58
     Forest
    0.47
    ;(
    0.45
     Develop
    0.44
     Concord
    0.44
     dugout
    0.44
    in
    0.44
     Poison
    0.44
     Developments
    0.44
    ;|
    0.42
    Activations Density 0.000%

    No Known Activations