© 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. 355
    Prev
    Next
    INDEX
    Explanations

    ways to split

    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
    و
    0.73
     دام
    0.63
    다
    0.61
    𝐬
    0.61
    宇宙
    0.61
    لك
    0.60
    Lastly
    0.60
    𝗅
    0.59
    து
    0.59
     Scientist
    0.59
    POSITIVE LOGITS
    égek
    0.93
    klar
    0.76
    ەن
    0.76
    ที่จะ
    0.76
     errorHandler
    0.76
     избежать
    0.75
    larni
    0.75
    ätta
    0.74
    ayvachi
    0.74
     år
    0.73
    Activations Density 1.331%

    No Known Activations