© 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. 198462
    Prev
    Next
    INDEX
    Explanations

    Protestants, cottages, TAX, perspective

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

    learning patterns

    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
    کل
    0.44
    酸素
    0.44
    DeleteItem
    0.44
     Восто
    0.44
    뮤
    0.43
    زاده
    0.43
    াতা
    0.42
    BeginInit
    0.42
    이너
    0.41
     ஏற்படுகிறது
    0.41
    POSITIVE LOGITS
     మూడు
    0.51
     पत्नी
    0.49
     ngưỡng
    0.48
     четы
    0.48
     teams
    0.47
     तीन
    0.46
     теп
    0.46
     պ
    0.45
    n
    0.44
    eh
    0.44
    Activations Density 0.001%

    No Known Activations