© 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
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2663
    Prev
    Next
    INDEX
    Explanations

    từ tiếng Việt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Чи
    0.84
    文字列
    0.84
    注意
    0.78
    刹
    0.78
    昨
    0.78
    段
    0.77
    कारे
    0.76
    WARN
    0.75
    鬼
    0.75
    Electric
    0.74
    POSITIVE LOGITS
     đã
    1.93
     đặc
    1.88
     bằng
    1.86
     thường
    1.84
     này
    1.83
     của
    1.83
     nói
    1.82
     khác
    1.81
     gồm
    1.80
     trước
    1.78
    Activations Density 0.002%

    No Known Activations