© 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. 234251
    Prev
    Next
    INDEX
    Explanations

    advisers, House, Management, Tube, done, Policy, alone

    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
     −
    0.53
     holdings
    0.51
     Argonne
    0.46
     ブラ
    0.45
     ¶
    0.44
     時計
    0.44
     brownies
    0.44
     odometer
    0.44
     digunakan
    0.44
     ٹیکسٹ
    0.44
    POSITIVE LOGITS
     כל
    0.55
    각
    0.54
    כל
    0.50
    每一
    0.48
    ك
    0.48
    我们要
    0.48
    fuck
    0.48
    各类
    0.48
    开关
    0.48
    we
    0.47
    Activations Density 0.000%

    No Known Activations