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. 973
    Prev
    Next
    INDEX
    Explanations

    arms control

    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
    腴
    0.77
     सूत्रों
    0.74
     вещи
    0.70
     Histogram
    0.68
     jumpsuit
    0.68
     seat
    0.64
    规律
    0.64
     кров
    0.63
    ница
    0.63
     zio
    0.63
    POSITIVE LOGITS
     sees
    0.78
     peeled
    0.71
     see
    0.70
    を見る
    0.69
    }\|^
    0.67
     raided
    0.66
    鈞
    0.66
     assassinated
    0.65
     reads
    0.65
     walks
    0.65
    Activations Density 0.000%

    No Known Activations