Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 4275
    Prev
    Next
    INDEX
    Explanations

    code delimiters and symbols

    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
    ή
    0.72
    낄
    0.72
    വം
    0.72
     কার্য
    0.70
     ความ
    0.69
    כים
    0.67
    ഗം
    0.66
    irdiği
    0.66
     zei
    0.65
    iciaire
    0.65
    POSITIVE LOGITS
    <span>
    0.90
    <0x0D>
    0.73
    enger
    0.61
     пожалуйста
    0.58
    ↵
    0.57
    ষ্ট
    0.57
    eger
    0.56
     یون
    0.55
    amic
    0.54
    なのです
    0.54
    Activations Density 0.364%

    No Known Activations