© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 200779
    Prev
    Next
    INDEX
    Explanations

    report after issue

    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/layer_31_width_262k_l0_medium
    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
    生地
    0.44
    燃料
    0.44
    证
    0.42
    ));
    0.42
     Yukon
    0.42
    スカート
    0.41
     CAL
    0.41
    番
    0.41
     saucer
    0.40
    生
    0.40
    POSITIVE LOGITS
    ‌ها
    0.52
     از
    0.52
    ology
    0.50
    ‌های
    0.49
     từ
    0.47
     weiterhin
    0.47
    Cite
    0.46
    larını
    0.46
    lardan
    0.46
     από
    0.46
    Activations Density 0.002%

    No Known Activations