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-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 5424
    Prev
    Next
    INDEX
    Explanations

    multilingual code explanations

    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_29_width_65k_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
    દાર
    0.72
    Swiss
    0.71
    ált
    0.69
    侗
    0.68
    ాలి
    0.67
     Viên
    0.66
    Something
    0.66
    🍕
    0.66
    imut
    0.66
    Burning
    0.66
    POSITIVE LOGITS
     צ
    0.74
     ト
    0.73
     cilia
    0.70
     本体
    0.70
    ご注文
    0.70
     Herbert
    0.70
     म्हणून
    0.68
     حضور
    0.67
     канцеля
    0.66
    털
    0.64
    Activations Density 0.011%

    No Known Activations