© 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. 22-GEMMASCOPE-RES-131K
    7. 73843
    Prev
    Next
    INDEX
    Explanations

    African countries and cities

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

    The neuron is detecting mentions of Ghana (e.g. “Ghana,” “Ghanaian,” or “Accra”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     conejo
    -1.02
     wako
    -1.01
     sicuramente
    -0.97
     pájaro
    -0.97
     沖縄
    -0.96
    Pont
    -0.96
    ianie
    -0.96
     hvil
    -0.95
    感じで
    -0.95
     pcx
    -0.92
    POSITIVE LOGITS
    鷺
    1.02
     Africa
    0.97
     African
    0.96
     equatorial
    0.93
    钧
    0.93
    Kariera
    0.89
     メーカー
    0.89
    rboles
    0.88
     インチ
    0.88
    modium
    0.88
    Activations Density 0.086%

    No Known Activations