© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90713
    Prev
    Next
    INDEX
    Explanations

    marriage record identifiers

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

    % interest rate followed by benefits

    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
     Orders
    0.49
     AF
    0.44
     Nhân
    0.44
     ந
    0.44
     Dünya
    0.43
     mercanc
    0.43
     environs
    0.43
     Err
    0.42
     USAF
    0.41
     È
    0.41
    POSITIVE LOGITS
    (),
    0.53
     pathogenicity
    0.51
    OKR
    0.50
    +
    0.49
    %
    0.49
    *
    0.48
    ковского
    0.48
    SCREEN
    0.48
    ACTIV
    0.47
    К
    0.47
    Activations Density 0.002%

    No Known Activations