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. 7504
    Prev
    Next
    INDEX
    Explanations

    visual appearance and aesthetics

    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
    ar
    1.01
    as
    0.98
    esque
    0.89
    ل
    0.88
    न
    0.86
    কৃত
    0.83
    ת
    0.83
    on
    0.83
    ール
    0.82
    oce
    0.82
    POSITIVE LOGITS
     meisten
    0.96
    ্যা
    0.87
     불구하고
    0.87
     sehen
    0.86
    ressant
    0.84
     Đáp
    0.84
     suffering
    0.82
    Ꮑ
    0.81
     zmi
    0.80
     significativa
    0.79
    Activations Density 0.162%

    No Known Activations