© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 8779
    Prev
    Next
    INDEX
    Explanations

    dialogue attributed to speakers

    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
    T
    0.81
     पढ़ें
    0.70
     T
    0.68
     pure
    0.67
    由
    0.63
    multicolumn
    0.63
     unscrupulous
    0.61
    M
    0.60
    정과
    0.60
    ='',
    0.59
    POSITIVE LOGITS
     Pourquoi
    1.36
     Почему
    1.28
     Presents
    1.25
     Когда
    1.24
     Много
    1.21
     Сьогодні
    1.20
     何
    1.19
    :...
    1.18
     vrijdag
    1.15
     连接
    1.14
    Activations Density 0.043%

    No Known Activations