© 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. 847
    Prev
    Next
    INDEX
    Explanations

    new, min, max

    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
    IRCONIUM
    0.69
     hydrolysis
    0.57
    醂
    0.57
    ُو
    0.56
    ปลี่ยน
    0.55
    ه‌ها
    0.55
    ឡិច
    0.54
    ウダー
    0.54
    FTWARE
    0.53
    ូត
    0.53
    POSITIVE LOGITS
    in
    0.63
    n
    0.55
    f
    0.55
    p
    0.54
    k
    0.54
    &#
    0.53
    1
    0.53
     Journal
    0.52
    ,
    0.52
    i
    0.52
    Activations Density 0.002%

    No Known Activations