© 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. 38661
    Prev
    Next
    INDEX
    Explanations

    p-values, page numbers, or prefixes

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

    p-adic, p-groups, primes

    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
    หลัก
    0.47
     звер
    0.46
     оригіналу
    0.46
    Graphical
    0.46
    .​
    0.45
    :)
    0.45
    Originally
    0.44
     основним
    0.43
    Carlo
    0.43
    Vere
    0.43
    POSITIVE LOGITS
    uene
    0.45
     soil
    0.45
    üş
    0.44
     parser
    0.43
     trucking
    0.42
    বাদ
    0.42
     Turkey
    0.41
     Space
    0.41
    ొప్పి
    0.39
    那
    0.39
    Activations Density 0.000%

    No Known Activations