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. 52825
    Prev
    Next
    INDEX
    Explanations

    National Geographic animals

    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
    的地
    0.73
    الیا
    0.72
     história
    0.71
    痨
    0.70
    墺
    0.68
     காட்சி
    0.68
    сса
    0.67
     partial
    0.66
     joke
    0.66
    isfile
    0.66
    POSITIVE LOGITS
     Cole
    0.72
     jab
    0.69
    gu
    0.69
    service
    0.66
    G
    0.63
     Service
    0.63
     On
    0.62
    દર્શન
    0.62
     забу
    0.62
    Service
    0.61
    Activations Density 0.012%

    No Known Activations