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. 8313
    Prev
    Next
    INDEX
    Explanations

    creating html elements

    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
     to
    -0.89
     above
    -0.85
     operated
    -0.84
     access
    -0.84
     reciben
    -0.84
    inosaur
    -0.81
    終わり
    -0.79
     чтоб
    -0.79
     held
    -0.79
     hosted
    -0.78
    POSITIVE LOGITS
    createElement
    1.16
    %;">
    0.98
     indirec
    0.97
     artesanal
    0.92
    لاین
    0.91
    "],
    
    0.91
     réservoir
    0.91
    创建一个
    0.89
    announced
    0.88
    🖖
    0.88
    Activations Density 0.004%

    No Known Activations