© 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
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 177
    Prev
    Next
    INDEX
    Explanations

    There's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_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
    ные
    0.89
    ный
    0.73
    nya
    0.70
     роботу
    0.69
    ীয়
    0.69
    I
    0.67
    і
    0.67
    ${
    0.66
    ♤
    0.66
    ных
    0.65
    POSITIVE LOGITS
    e
    1.03
    ו
    0.78
    britannien
    0.72
    ে
    0.72
    iou
    0.69
    hoy
    0.67
    種の
    0.66
    го
    0.66
    კ
    0.65
    𝗴
    0.65
    Activations Density 1.099%

    No Known Activations