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. 52763
    Prev
    Next
    INDEX
    Explanations

    special characters in URLs

    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
     Capp
    0.80
     mignon
    0.74
     rheumat
    0.71
     Rheumat
    0.71
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.67
    oplankton
    0.67
    Capp
    0.66
     IH
    0.65
     ი
    0.64
     pox
    0.64
    POSITIVE LOGITS
    isième
    0.69
     vrat
    0.65
    マス
    0.65
     நிற்கும்
    0.65
    Nan
    0.63
     وقف
    0.63
    гото
    0.62
    ampoo
    0.61
    גי
    0.61
     மொ
    0.61
    Activations Density 0.006%

    No Known Activations