© 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. 1137
    Prev
    Next
    INDEX
    Explanations

    events, holidays, history, tickets, newspaper

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

    この素晴らしい放送大学これはゾンビ

    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
    सामान्यीकृत
    0.78
    स्करण
    0.71
     tcpHeader
    0.70
    نګه
    0.69
    嫵
    0.68
    दिग्ध
    0.68
    अधिकांश
    0.68
    鸪
    0.67
    𝙚
    0.66
    𝙝
    0.66
    POSITIVE LOGITS
    ・
    0.96
    お
    0.88
    1
    0.85
    のお
    0.79
    7
    0.77
    <0xE3>
    0.76
    の
    0.76
    ～
    0.76
    0.76
    、
    0.75
    Activations Density 0.007%

    No Known Activations