Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 1231
    Prev
    Next
    INDEX
    Explanations

    time series

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    в
    1.91
     vezi
    1.73
    おります
    1.70
    ﺀ
    1.70
    🤧
    1.68
     sympathize
    1.67
    ug
    1.66
    页面存档备份
    1.66
     valable
    1.63
    を引き
    1.62
    POSITIVE LOGITS
    tır
    2.36
    ب
    2.36
    특별시
    2.31
    tions
    2.23
    tion
    2.19
    ted
    2.17
    tak
    2.11
    ी
    2.11
    تو
    2.09
    eer
    2.08
    Activations Density 0.452%

    No Known Activations