© 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. 250658
    Prev
    Next
    INDEX
    Explanations

    . locals

    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
    Not in Any Lists

    No Comments

    Negative Logits
     మొదటి
    0.45
     Rui
    0.43
     first
    0.42
     première
    0.41
     پہلی
    0.40
    .​​
    0.38
     mezzanine
    0.38
     premières
    0.37
     Unexpected
    0.37
     ആദ്യ
    0.37
    POSITIVE LOGITS
    ಗ್
    0.48
     आतंकवादी
    0.47
     ব্যার্থ
    0.44
    殺人
    0.43
     автомоби
    0.42
    restaurants
    0.42
    娯
    0.41
    这些人
    0.40
     সহিংস
    0.40
     автомо
    0.39
    Activations Density 0.001%

    No Known Activations