© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 23456
    Prev
    Next
    INDEX
    Explanations

    Uganda

    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
     ndani
    -0.86
    柠檬
    -0.79
    Sting
    -0.77
     kufanya
    -0.77
     Broccoli
    -0.75
    Pome
    -0.74
     Pome
    -0.73
     بني
    -0.73
     kwamba
    -0.73
     kuhusu
    -0.73
    POSITIVE LOGITS
     Uganda
    2.53
     Ugandan
    2.23
    Uganda
    1.91
    Ug
    1.52
     Kampala
    1.48
     Ug
    1.30
     Kenya
    1.10
     Nairobi
    1.05
     shillings
    1.01
     Ente
    0.97
    Activations Density 0.030%

    No Known Activations