© 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. 217281
    Prev
    Next
    INDEX
    Explanations

    found a

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

    Author Platform

    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
     tais
    0.50
     लेकिन
    0.48
    //
    0.44
     那
    0.43
    厌
    0.43
    tdown
    0.43
     znaleźć
    0.42
     exceeded
    0.42
     nhưng
    0.42
    (|
    0.42
    POSITIVE LOGITS
    விக்கும்
    0.46
    ക്കൊ
    0.45
    SHRI
    0.43
    marvel
    0.43
    합
    0.43
    lomer
    0.41
    NOWLEDG
    0.41
    estim
    0.40
    됩니다
    0.39
    CPI
    0.39
    Activations Density 0.001%

    No Known Activations