© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4123
    Prev
    Next
    INDEX
    Explanations

    file contains or is

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

    describing initializer files

    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
    டனும்
    0.55
    ９
    0.55
    ქვთ
    0.54
    ๖
    0.54
    𝟕
    0.54
    ۷
    0.53
    ๗
    0.52
     ಅರ್ಜಿ
    0.51
     ಪುಸ್ತಕ
    0.50
    ٧
    0.50
    POSITIVE LOGITS
     is
    0.63
    0.55
     wur
    0.51
     merupakan
    0.51
     adalah
    0.50
     ne
    0.50
     im
    0.48
     Dai
    0.48
     [
    0.48
     he
    0.47
    Activations Density 0.000%

    No Known Activations