© 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. 71120
    Prev
    Next
    INDEX
    Explanations

    website or real people

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

    at for

    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
     ಹೇಳ
    0.53
     абсолю
    0.53
    efficacité
    0.52
     явно
    0.52
     ефектив
    0.51
     эффективность
    0.50
     честь
    0.50
     память
    0.50
    亢
    0.50
    herent
    0.48
    POSITIVE LOGITS
     creations
    0.57
     picker
    0.54
     shortcuts
    0.52
     blueprint
    0.51
     textarea
    0.51
     direction
    0.50
     favourites
    0.50
     layouts
    0.50
     tortoises
    0.50
     locations
    0.49
    Activations Density 0.001%

    No Known Activations