© 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. 179694
    Prev
    Next
    INDEX
    Explanations

    X and/or Y

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

    inserting or printing 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
    族
    0.50
    ing
    0.49
    เภท
    0.49
    行った
    0.46
    ੈਂ
    0.43
    。《
    0.43
    者
    0.43
    護
    0.43
    erde
    0.42
    麗
    0.42
    POSITIVE LOGITS
     പുറ
    0.52
    getMy
    0.51
    getEmail
    0.51
    restaurants
    0.50
     चाहिये
    0.50
     матрицы
    0.50
    Arrays
    0.50
    ariş
    0.50
    seats
    0.50
    trashButton
    0.49
    Activations Density 0.000%

    No Known Activations