© 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. 205081
    Prev
    Next
    INDEX
    Explanations

    p: followed by arguments

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

    p followed by non-alphanumeric

    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
     उल्
    0.48
     घड
    0.44
     រ
    0.44
    কাহিনী
    0.44
     прадстаў
    0.43
     बिलियन
    0.43
     ओटी
    0.42
     vegetative
    0.42
     खरे
    0.41
    institut
    0.41
    POSITIVE LOGITS
    THERE
    0.46
    adb
    0.44
    *
    0.41
    yy
    0.40
     rspace
    0.40
     escalar
    0.39
     perspectiva
    0.39
    [
    0.39
    <
    0.39
    ##
    0.39
    Activations Density 0.003%

    No Known Activations