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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 967
    Prev
    Next
    INDEX
    Explanations

    margin or maximum

    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_262k_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
    figuration
    0.73
    formed
    0.72
    급
    0.69
    했다고
    0.67
     unresponsive
    0.67
    braska
    0.67
    MyToolkit
    0.67
    ร่าง
    0.67
    hFile
    0.66
     파일
    0.66
    POSITIVE LOGITS
     Max
    0.76
     max
    0.75
     νό
    0.69
    max
    0.66
     memak
    0.66
     Maximum
    0.66
     q
    0.66
     leth
    0.65
     শাক
    0.65
    iro
    0.64
    Activations Density 0.001%

    No Known Activations