© 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. 173955
    Prev
    Next
    INDEX
    Explanations

    copyright infringement

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

    card, cost, or report

    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
    BeerItem
    0.51
     иной
    0.50
    точ
    0.50
    পানি
    0.49
    бри
    0.49
     саме
    0.49
     চু
    0.48
     ступен
    0.48
    ﾗ
    0.48
    ராம
    0.48
    POSITIVE LOGITS
    var
    0.59
    Mer
    0.58
    ir
    0.57
    3
    0.57
    1
    0.52
    msubsup
    0.50
    8
    0.50
    ines
    0.49
    mer
    0.49
    in
    0.48
    Activations Density 0.001%

    No Known Activations