© 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. 80442
    Prev
    Next
    INDEX
    Explanations

    creation and action verbs

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

    throwing a

    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
     Fruits
    0.51
     ২০১৬
    0.49
     Jimin
    0.48
     [])
    0.48
     Uranus
    0.47
    ;*/
    0.46
     Carlo
    0.45
     ബി
    0.44
    การณ์
    0.44
    鴛
    0.44
    POSITIVE LOGITS
    ну
    0.49
    боро
    0.48
    ખ
    0.48
    ле
    0.48
    лся
    0.48
    ထ
    0.47
     جای
    0.45
    три
    0.45
     réserve
    0.45
    স্টে
    0.44
    Activations Density 0.000%

    No Known Activations