© 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. 87252
    Prev
    Next
    INDEX
    Explanations

    data privacy statement purpose

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

    servers, contracts, validation

    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
    sop
    0.51
    Ад
    0.46
    alista
    0.44
    盞
    0.44
    ilitar
    0.44
     ثلاثة
    0.44
    ទំនាក់ទំនង
    0.43
    Eso
    0.43
    ureate
    0.43
    soph
    0.43
    POSITIVE LOGITS
     to
    0.49
    休息
    0.46
     Shibuya
    0.46
     plantel
    0.46
     Stephen
    0.45
     getId
    0.43
     jste
    0.42
     फैक्ट्री
    0.42
    昔
    0.42
     bào
    0.42
    Activations Density 0.001%

    No Known Activations