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-16K
    4. 82
    Prev
    Next
    INDEX
    Explanations

    code structure

    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_16k_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
     
    0.59
    e
    0.54
    :
    0.52
    ,
    0.52
     (
    0.51
     in
    0.50
     you
    0.50
      
    0.50
     reproduced
    0.50
     e
    0.49
    POSITIVE LOGITS
     rctx
    0.81
    liono
    0.80
     errorHandler
    0.80
     txtbtn
    0.79
    льнявыя
    0.79
    𐰴
    0.78
    ómago
    0.77
     Paryayvachi
    0.77
    𒉺
    0.76
    Ⲁ
    0.76
    Activations Density 0.582%

    No Known Activations