© 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. 179987
    Prev
    Next
    INDEX
    Explanations

    on when, state, counselor, category

    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
    ંને
    0.50
     വിൽപ്പന
    0.50
     ਦਵਾਈ
    0.50
     پیسې
    0.49
     vutto
    0.49
     аўтаматы
    0.48
    👼
    0.48
    二百
    0.48
    フード
    0.47
    かわらず
    0.47
    POSITIVE LOGITS
     “
    0.56
     a
    0.50
     traditional
    0.50
     t
    0.49
     Prussian
    0.47
     {$
    0.46
     (
    0.46
     k
    0.46
     inappropriately
    0.46
     their
    0.44
    Activations Density 0.001%

    No Known Activations