© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 388
    Prev
    Next
    INDEX
    Explanations

    electrical components and technologies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    brightness
    0.67
    ាតុ
    0.63
    ើន
    0.59
    繁忙時間服務
    0.59
    <unused706>
    0.59
     geometrical
    0.59
    リーム
    0.59
    ួរ
    0.59
    ه‌ها
    0.59
    configuring
    0.59
    POSITIVE LOGITS
     бушлай
    0.63
    들
    0.57
     Journalist
    0.55
    이
    0.55
     Graffiti
    0.54
    &#
    0.54
    보다
    0.54
     해외
    0.54
    에
    0.54
    로
    0.54
    Activations Density 2.378%

    No Known Activations