© 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. 124285
    Prev
    Next
    INDEX
    Explanations

    personalized license plates

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

    depending on when or where

    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
    USERS
    0.57
    프로
    0.51
     '');
    0.50
    न्
    0.50
    غيل
    0.50
    ０
    0.50
    帀
    0.49
    "];
    0.49
    モダン
    0.48
    marshalO
    0.48
    POSITIVE LOGITS
     be
    0.57
     we
    0.50
     case
    0.50
    ↵↵
    0.47
     was
    0.45
     Guar
    0.44
     Mur
    0.43
     heartwarming
    0.43
     or
    0.43
     grad
    0.43
    Activations Density 0.002%

    No Known Activations