© 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. 39053
    Prev
    Next
    INDEX
    Explanations

    information and assistance

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

    specific keywords and following tokens

    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
    2
    0.53
    Chia
    0.49
    4
    0.47
    5
    0.47
    пи
    0.45
    優
    0.45
    ショ
    0.44
    ги
    0.43
    Pi
    0.43
    お願い致します
    0.43
    POSITIVE LOGITS
    honneur
    0.49
     ሌሎች
    0.47
     파일
    0.45
     بنگالی
    0.44
    elihood
    0.43
    ustral
    0.43
     priors
    0.43
    ಾನ್
    0.43
    itriangular
    0.43
     አንዳንድ
    0.43
    Activations Density 0.000%

    No Known Activations