Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7544
    Prev
    Next
    INDEX
    Explanations

    essay requests

    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
     सटे
    2.87
    ই
    2.75
    windigkeit
    2.74
    ার
    2.72
    र
    2.67
    ို့
    2.67
     roaring
    2.66
    あります
    2.65
     behold
    2.65
    齬
    2.63
    POSITIVE LOGITS
    ва
    3.66
    м
    3.38
    ../../
    3.17
     decía
    3.02
    പ്പെട്ട
    2.89
     koje
    2.84
    راہیم
    2.81
    
    2.78
    мся
    2.77
     ausgezeichnet
    2.77
    Activations Density 0.104%

    No Known Activations