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. 8213
    Prev
    Next
    INDEX
    Explanations

    Catherine Middleton and royals

    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
    
    -0.79
    Detroit
    -0.76
    älfte
    -0.75
    ederos
    -0.73
     motivasi
    -0.73
    独特
    -0.72
     fuerte
    -0.72
    ঋ
    -0.71
    リスト
    -0.71
    extent
    -0.71
    POSITIVE LOGITS
     Middleton
    1.45
     Kate
    1.07
     Catherine
    1.04
     Carole
    1.00
     royal
    0.96
    Catherine
    0.89
     William
    0.87
    Carole
    0.87
     Cambridge
    0.84
     Bhutan
    0.84
    Activations Density 0.006%

    No Known Activations