© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30266
    Prev
    Next
    INDEX
    Explanations

    ambassador and diplomat locations

    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
    元年
    -0.85
     pierde
    -0.79
     امروز
    -0.77
    kose
    -0.77
     operated
    -0.76
    '.
    -0.75
     ὑ
    -0.75
    
    -0.75
     emberek
    -0.74
    一個
    -0.72
    POSITIVE LOGITS
     Moscow
    1.02
     Cairo
    0.97
    menor
    0.96
     Ankara
    0.95
     Madrid
    0.91
     UNESCO
    0.90
     Rome
    0.89
     Brasília
    0.88
     Canberra
    0.88
     Wellington
    0.88
    Activations Density 0.018%

    No Known Activations