© 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. 38535
    Prev
    Next
    INDEX
    Explanations

    Zambian national organizations

    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
     kuan
    -1.00
     hina
    -0.99
     trover
    -0.95
     alip
    -0.94
     rangi
    -0.93
    ändig
    -0.91
    𝕂
    -0.88
    
    -0.87
     niedersachsen
    -0.86
     utaf
    -0.85
    POSITIVE LOGITS
     Zambia
    1.69
     Zamb
    1.41
    Zambia
    1.33
     Lusaka
    1.22
     Copper
    1.14
     Edgar
    1.11
    Copper
    1.09
     PF
    1.05
     Z
    1.01
     Chis
    0.98
    Activations Density 0.034%

    No Known Activations