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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 2119
    Prev
    Next
    INDEX
    Explanations

    code syntax and web elements

    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_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
    an
    0.63
    a
    0.63
    als
    0.58
     an
    0.57
    e
    0.57
    is
    0.56
    i
    0.56
    he
    0.56
    1
    0.54
     different
    0.53
    POSITIVE LOGITS
     noreferrer
    0.76
     或
    0.73
     அல்லது
    0.72
    StringEncoding
    0.70
     अथवा
    0.70
    чными
    0.69
     outputFile
    0.69
     या
    0.69
    ټبال
    0.68
     podendo
    0.68
    Activations Density 0.552%

    No Known Activations