© 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. 91098
    Prev
    Next
    INDEX
    Explanations

    for you and others

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

    inwards collapsed, Protect time

    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
     cruises
    0.48
     contributes
    0.45
     biota
    0.45
     periodicals
    0.44
    깃
    0.41
     yarns
    0.41
    パン
    0.41
     bioinformatics
    0.40
     draws
    0.39
     microorganism
    0.39
    POSITIVE LOGITS
    dbh
    0.53
    nThe
    0.50
     Г
    0.49
     ढक
    0.48
     ketiga
    0.46
    leb
    0.46
    ihe
    0.46
     трёх
    0.45
    т
    0.45
     आपला
    0.45
    Activations Density 0.000%

    No Known Activations