© 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. 85083
    Prev
    Next
    INDEX
    Explanations

    versus or find or something or in or while or the or those or should

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

    proteins, biological, values

    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
     seals
    0.53
     newfound
    0.53
     réc
    0.53
     总
    0.51
     liner
    0.49
     bulls
    0.49
     spans
    0.48
     skepticism
    0.48
     shipper
    0.48
     liners
    0.48
    POSITIVE LOGITS
    Tim
    0.51
    Ви
    0.50
    Ро
    0.49
    ."[
    0.49
    เมื่อ
    0.48
    attro
    0.47
    Доб
    0.47
    .");
    0.46
    勍
    0.46
    larak
    0.45
    Activations Density 0.001%

    No Known Activations