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-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8476
    Prev
    Next
    INDEX
    Explanations

    members of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     وت
    -0.90
     acoged
    -0.75
    YSTAL
    -0.75
    Which
    -0.74
     большие
    -0.73
     ظل
    -0.73
     και
    -0.73
    kespea
    -0.73
     paragraphe
    -0.72
     и
    -0.71
    POSITIVE LOGITS
     of
    2.63
     ofthe
    1.19
     academia
    0.97
     laity
    0.96
     của
    0.96
     bouw
    0.96
     ensimmä
    0.91
    ของ
    0.91
    )));
    
    0.91
     suiker
    0.90
    Activations Density 0.023%

    No Known Activations