© 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. 75569
    Prev
    Next
    INDEX
    Explanations

    African countries and their institutions

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects the presence of country or region names (geopolitical place names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    mentions of African countries and closely related national institutions or identifiers

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "Kenya" and similar African country names, especially when followed by organizational or governmental terms.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    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
    ïde
    -0.81
    ният
    -0.80
     faſt
    -0.78
     Italijanski
    -0.77
    aysia
    -0.77
     دوباره
    -0.75
    GITHUB
    -0.75
    町
    -0.74
     cauliflower
    -0.74
    actéristique
    -0.73
    POSITIVE LOGITS
     Revenue
    1.43
     Airways
    1.15
     Brewer
    1.12
     Railways
    1.05
     Development
    1.03
     National
    1.02
     Broadcasting
    1.00
     Electricity
    0.98
     Ports
    0.96
     Institute
    0.94
    Activations Density 0.027%

    No Known Activations