© 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. 211368
    Prev
    Next
    INDEX
    Explanations

    parts, bits, minutes, or specific entities

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

    the substitution command

    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
    ב
    0.55
     gồm
    0.54
    в
    0.52
    NOVEMBER
    0.51
    рая
    0.50
    ложено
    0.50
    這
    0.48
    データ
    0.47
     toán
    0.47
     nhìn
    0.47
    POSITIVE LOGITS
     حصے
    0.48
    %；
    0.48
     Communities
    0.46
    hmann
    0.45
    communities
    0.44
    il
    0.43
    tariff
    0.43
    schw
    0.41
    sonaro
    0.41
    ir
    0.40
    Activations Density 0.001%

    No Known Activations