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. 22-GEMMASCOPE-2-RES-65K
    4. 3347
    Prev
    Next
    INDEX
    Explanations

    web links

    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
    inskii
    0.88
     GitHub
    0.86
    GitHub
    0.85
     Github
    0.83
     NIH
    0.81
    洧
    0.81
    萫
    0.80
     git
    0.77
     quark
    0.76
    Github
    0.75
    POSITIVE LOGITS
    www
    1.20
     www
    1.04
     کاروب
    0.81
    stores
    0.81
    WWW
    0.71
     Bewer
    0.71
    static
    0.69
     కాదు
    0.67
    unread
    0.67
    恕
    0.66
    Activations Density 0.034%

    No Known Activations