© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 10500
    Prev
    Next
    INDEX
    Explanations

    training actions

    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_17_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
    itary
    3.22
    ্স
    2.75
    ური
    2.71
     refroidissement
    2.66
    skjaer
    2.62
    खी
    2.61
    ри
    2.60
    د
    2.60
    arı
    2.58
    йки
    2.56
    POSITIVE LOGITS
    */
    3.10
    야
    2.83
    ي
    2.80
     CGRect
    2.74
    ありますが
    2.69
    лл
    2.62
    mill
    2.59
    ΟΣ
    2.58
    বন্ত
    2.57
    ยนต์
    2.55
    Activations Density 1.027%

    No Known Activations