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. 882
    Prev
    Next
    INDEX
    Explanations

    people laughing

    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
    畬
    0.74
    പ്പം
    0.72
    ާތ
    0.68
    iez
    0.66
     Jana
    0.66
    ூன்
    0.66
    seeking
    0.66
    졍
    0.66
     coloc
    0.63
    請求
    0.62
    POSITIVE LOGITS
     laugh
    3.61
     laughing
    3.54
     laughs
    3.53
     laughter
    3.52
     laughed
    3.44
     chuckle
    3.30
     Laugh
    3.29
    Laugh
    3.27
     chuckled
    3.26
    laugh
    3.09
    Activations Density 0.147%

    No Known Activations