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. 723
    Prev
    Next
    INDEX
    Explanations

    presentation and communication

    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
    ังหวัด
    0.67
     निकलने
    0.66
     सब्सक्राइब
    0.65
    关键字
    0.65
    writable
    0.64
     scanf
    0.63
     نکل
    0.63
    鲮
    0.63
    孳
    0.62
     LUMPUR
    0.62
    POSITIVE LOGITS
     presenting
    4.87
     presentation
    4.75
     presented
    4.62
     Presentation
    4.41
     presents
    4.24
     presentations
    4.22
     Presented
    4.22
    Presentation
    4.20
    presented
    4.17
    presentation
    4.15
    Activations Density 0.438%

    No Known Activations