© 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. 16-GEMMASCOPE-2-RES-262K
    7. 2341
    Prev
    Next
    INDEX
    Explanations

    code block endings

    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_16_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
     is
    0.82
     بر
    0.68
     of
    0.65
     شب
    0.64
    ర్థిక
    0.64
     بال
    0.63
     త
    0.63
    ^{*}}\
    0.63
    0.63
     យើង
    0.62
    POSITIVE LOGITS
    s
    0.93
    ों
    0.88
    น
    0.85
    ó
    0.83
    ب
    0.78
    س
    0.76
    ы
    0.75
    이
    0.75
    ม
    0.75
    न
    0.73
    Activations Density 0.320%

    No Known Activations