© 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. 31-GEMMASCOPE-2-RES-262K
    7. 43948
    Prev
    Next
    INDEX
    Explanations

    specific requirements

    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_31_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
     пул
    0.50
    ב
    0.49
     समुद्री
    0.47
     процессо
    0.47
     furl
    0.46
     النظر
    0.46
     ори
    0.46
     полити
    0.46
     البيانات
    0.46
     نیر
    0.46
    POSITIVE LOGITS
    dense
    0.59
    ed
    0.54
    in
    0.53
    as
    0.48
    atious
    0.46
    /
    0.46
    table
    0.46
    grid
    0.46
    datatables
    0.45
    defined
    0.45
    Activations Density 0.001%

    No Known Activations