© 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. 175989
    Prev
    Next
    INDEX
    Explanations

    risk, has, seeing, brunch, answer, old

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

    teasing, though, some theorize

    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
    ע
    0.58
    Hasil
    0.54
    Asalamualaikum
    0.53
    ב
    0.48
    Revenue
    0.47
    ございます
    0.46
    Nice
    0.45
    Purch
    0.45
    Electric
    0.44
    Ever
    0.44
    POSITIVE LOGITS
    ซ์
    0.52
    $
    0.52
    ích
    0.52
     سريع
    0.52
    iques
    0.49
     বাড়তি
    0.49
     national
    0.48
     場
    0.48
    梢
    0.48
     ウェ
    0.48
    Activations Density 0.001%

    No Known Activations