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. 7509
    Prev
    Next
    INDEX
    Explanations

    death and dying

    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
    ^{-}
    2.16
     idiot
    2.01
     educativos
    1.91
     uninhab
    1.87
    랫폼
    1.87
     idiots
    1.86
     highlands
    1.85
     Upcoming
    1.82
     herbs
    1.81
    تدائي
    1.81
    POSITIVE LOGITS
    ंट
    1.75
    д
    1.74
    blood
    1.68
    অন্যদিকে
    1.66
    ure
    1.65
     мозга
    1.60
     penalty
    1.58
    カイブ
    1.54
    preventDefault
    1.54
    పోయ
    1.54
    Activations Density 0.217%

    No Known Activations