© 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. 172310
    Prev
    Next
    INDEX
    Explanations

    net proceeds

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

    duty, definition, trait, genre

    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
    اد
    0.54
    抧
    0.48
    यहां
    0.46
     图片
    0.44
    .],
    0.44
    ;',
    0.44
    峼
    0.44
     aggi
    0.44
    ustrated
    0.43
     docentes
    0.42
    POSITIVE LOGITS
    sila
    0.45
    fog
    0.45
    rope
    0.44
    luca
    0.43
    lak
    0.43
    勒
    0.43
    엑
    0.43
     saddle
    0.42
    ‐
    0.41
     Rye
    0.40
    Activations Density 0.000%

    No Known Activations