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. 22-GEMMASCOPE-2-RES-65K
    4. 3711
    Prev
    Next
    INDEX
    Explanations

    AI Chatbot

    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_22_width_65k_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
     собственной
    0.82
    Stage
    0.73
    ترى
    0.72
    तीश
    0.72
     ஏ
    0.71
     anywhere
    0.69
    Glad
    0.68
    蜷
    0.67
     operativa
    0.67
     worry
    0.67
    POSITIVE LOGITS
     وجہ
    0.81
     woord
    0.78
     섬
    0.77
     nád
    0.73
    website
    0.70
     ()=>
    0.69
     counties
    0.68
    ()==
    0.68
    िं
    0.67
     сообщение
    0.66
    Activations Density 0.029%

    No Known Activations