© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 49612
    Prev
    Next
    INDEX
    Explanations

    shrimp, prawns, noodles

    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
    ال
    1.00
    ية
    0.95
    a
    0.92
    。
    0.85
    ט
    0.85
    '
    0.78
    الأ
    0.76
    0
    0.75
    '>
    0.72
    ur
    0.72
    POSITIVE LOGITS
     on
    0.79
    irt
    0.71
     borg
    0.70
     incentiv
    0.70
    و
    0.68
    ικού
    0.68
    মনের
    0.68
    奻
    0.68
     inmobili
    0.67
    ள்ளதாக
    0.67
    Activations Density 0.001%

    No Known Activations