© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 26717
    Prev
    Next
    INDEX
    Explanations

    HTML `script`, `canvas`, `audio` tags

    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
    ;
    1.23
     is
    1.07
    $.
    1.02
    ।
    1.00
     for
    0.98
    ING
    0.98
     as
    0.97
    。
    0.94
    A
    0.88
    $).
    0.86
    POSITIVE LOGITS
    <0x80>
    0.99
    м
    0.91
    ம்
    0.86
    ních
    0.78
     všechny
    0.77
     جوړونکی
    0.76
    <0x94>
    0.75
    số
    0.73
     été
    0.72
     automática
    0.72
    Activations Density 0.019%

    No Known Activations