© 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. 117963
    Prev
    Next
    INDEX
    Explanations

    focal plane

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

    TikTok Syrian communication

    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
     optimizing
    0.49
     거고
    0.48
     bạn
    0.46
     crucified
    0.46
    があれば
    0.46
    _{{\
    0.45
     erosion
    0.44
    でしたが
    0.44
     agnostic
    0.44
     ізо
    0.44
    POSITIVE LOGITS
    liš
    0.53
    Background
    0.49
    Request
    0.46
    Message
    0.44
     svojim
    0.44
    šek
    0.44
    வாய
    0.43
    Restaurant
    0.43
    a
    0.43
     Bauern
    0.42
    Activations Density 0.001%

    No Known Activations