© 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. 119846
    Prev
    Next
    INDEX
    Explanations

    front zipper and pocket

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

    financial productivity transactions

    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
    Negative Logits
     கொலை
    0.47
    robespierre
    0.46
     contando
    0.46
    šen
    0.45
     緊急
    0.44
     न्याय
    0.44
    according
    0.43
     (%
    0.43
     endangering
    0.43
    odymyr
    0.42
    POSITIVE LOGITS
    Assets
    0.48
    Equity
    0.45
    AssetsRequest
    0.45
    箓
    0.45
    Burn
    0.43
     Wishes
    0.43
    Href
    0.43
    规划
    0.42
     Assets
    0.42
     charters
    0.41
    Activations Density 0.002%

    No Known Activations