© 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. 220260
    Prev
    Next
    INDEX
    Explanations

    insurance

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

    ancient egyptians, style robot, calorie addition

    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
    ഌ
    0.49
    ਨ
    0.48
     enviable
    0.47
    Сі
    0.46
    当時
    0.46
    ſed
    0.46
    퐫
    0.44
    諰
    0.44
    ネルギー
    0.44
    演員
    0.43
    POSITIVE LOGITS
    0
    0.57
     M
    0.54
    controller
    0.53
    table
    0.52
    controllers
    0.52
     %
    0.51
    horizontal
    0.51
    Controller
    0.48
     ಇನ್ನ
    0.46
     abgeschlossen
    0.45
    Activations Density 0.002%

    No Known Activations