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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58211
    Prev
    Next
    INDEX
    Explanations

    West African countries and cities

    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
     looking
    -0.78
    Looking
    -0.74
     Kenyans
    -0.73
    Provincial
    -0.73
     приви
    -0.72
     stringBuilder
    -0.70
    insk
    -0.70
    Debido
    -0.69
    rosa
    -0.67
     Provincia
    -0.66
    POSITIVE LOGITS
     Burkina
    1.28
    Mali
    1.22
     Benin
    1.19
     Senegal
    1.15
     Ghana
    1.15
     Mali
    1.13
     Accra
    1.10
     Ghanaian
    1.07
     Liberia
    1.03
    Ghana
    1.02
    Activations Density 0.013%

    No Known Activations