© 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. 207062
    Prev
    Next
    INDEX
    Explanations

    events and history

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

    describing origins or locations

    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
     author
    0.59
     Author
    0.55
     in
    0.50
     initialization
    0.50
     Obit
    0.50
     I
    0.49
     invocation
    0.49
     ad
    0.48
     Ruta
    0.48
     univ
    0.48
    POSITIVE LOGITS
    অল
    0.49
    auschen
    0.48
    
    0.48
     балко
    0.48
    ến
    0.47
    рино
    0.47
    refrac
    0.47
    extré
    0.46
    囱
    0.46
    ⃖
    0.46
    Activations Density 0.001%

    No Known Activations