© 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. 109998
    Prev
    Next
    INDEX
    Explanations

    prevent cavities. bacteria. have the

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

    bundle, optimized, scripts

    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
     lia
    0.46
    ;
    0.45
     trast
    0.45
     meetup
    0.45
     assisting
    0.43
     servitude
    0.43
     facilitation
    0.42
     degrad
    0.42
     repatriation
    0.42
     permit
    0.41
    POSITIVE LOGITS
     [$
    0.43
    NewUrl
    0.43
     қол
    0.43
    ник
    0.43
    就开始
    0.43
    низу
    0.43
    тать
    0.42
     страхо
    0.42
    ^+,
    0.42
    îtier
    0.42
    Activations Density 0.001%

    No Known Activations