© 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. 16217
    Prev
    Next
    INDEX
    Explanations

    Italian food

    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
     diverso
    0.67
     permettent
    0.62
     позволяют
    0.61
    菽
    0.59
    是
    0.58
    ཎ
    0.57
     tecnica
    0.57
    的
    0.57
     mismas
    0.56
    [*][[
    0.56
    POSITIVE LOGITS
    in
    0.88
    ad
    0.85
    il
    0.75
    p
    0.71
    त्य
    0.70
    to
    0.69
    ak
    0.68
    ay
    0.65
    ap
    0.65
    าย
    0.65
    Activations Density 0.007%

    No Known Activations