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. 29-GEMMASCOPE-2-RES-262K
    4. 766
    Prev
    Next
    INDEX
    Explanations

    python code

    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
     repente
    0.68
     Vy
    0.68
     Seo
    0.67
     Sé
    0.67
    ၎
    0.67
     Sunset
    0.66
     Sext
    0.65
    \},\{
    0.65
     SEO
    0.65
     Reveal
    0.65
    POSITIVE LOGITS
    т
    0.87
    脚本
    0.84
    script
    0.83
     script
    0.80
     البرنامج
    0.79
     scripts
    0.77
    import
    0.76
     importer
    0.75
    ٣
    0.75
     cargos
    0.74
    Activations Density 0.046%

    No Known Activations