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. 9-GEMMASCOPE-2-RES-262K
    4. 7377
    Prev
    Next
    INDEX
    Explanations

    famous historical figures

    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_9_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
    [],
    0.88
     ​​
    0.87
     koje
    0.85
     kaya
    0.83
     toko
    0.81
    Noun
    0.80
    nytimes
    0.80
    at
    0.79
    디
    0.79
     celeb
    0.79
    POSITIVE LOGITS
    丷
    0.92
    ஞ்ஞான
    0.91
    jší
    0.87
     Bài
    0.86
    esque
    0.86
    unov
    0.86
    ův
    0.85
    ли
    0.84
    кові
    0.82
    ن
    0.81
    Activations Density 0.190%

    No Known Activations