© 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. 79070
    Prev
    Next
    INDEX
    Explanations

    hereafter permitted, for any, all we, they can, judgement on, following location

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

    Bitcoin and Chinese text

    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
    evil
    0.48
    <0xB7>
    0.47
    Evil
    0.47
     ",
    0.46
    ั่ง
    0.43
    SELL
    0.43
    scenes
    0.43
    dataTable
    0.42
    ла
    0.42
    দ্রোহ
    0.42
    POSITIVE LOGITS
    有点
    0.49
     مدارس
    0.49
    萱
    0.48
     داشتن
    0.48
     relativement
    0.47
    蕗
    0.47
     singly
    0.46
    이자
    0.46
     оказалось
    0.45
    බ්
    0.45
    Activations Density 0.002%

    No Known Activations