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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7946
    Prev
    Next
    INDEX
    Explanations

    civic councillors zones

    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
    πέ
    -0.77
    Provincial
    -0.76
     Provincial
    -0.76
     Andra
    -0.72
    regierung
    -0.72
     Бар
    -0.72
    inescent
    -0.72
    马克
    -0.71
    daa
    -0.70
    ske
    -0.70
    POSITIVE LOGITS
     civic
    1.20
     zones
    0.98
     ward
    0.95
     zone
    0.92
     councillors
    0.90
     Zones
    0.88
    Zone
    0.88
     Civic
    0.87
     councillor
    0.85
     Zone
    0.85
    Activations Density 0.006%

    No Known Activations