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. 22-GEMMASCOPE-2-RES-65K
    4. 3536
    Prev
    Next
    INDEX
    Explanations

    clarifying phrases followed by comma

    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_22_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
    성과
    0.77
    性和
    0.75
     sekä
    0.72
     কিন্তু
    0.72
     \&
    0.71
    并将
    0.71
     Приступљено
    0.70
     മാത്രമല്ല
    0.69
     మరియు
    0.68
     Гар
    0.68
    POSITIVE LOGITS
    ,
    2.20
    ،
    2.03
    ,
    1.68
    ,-
    1.63
    ,(
    1.54
    、
    1.46
    ,:
    1.45
    ,.
    1.40
    -,
    1.39
    ®,
    1.34
    Activations Density 0.451%

    No Known Activations