© 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. 35715
    Prev
    Next
    INDEX
    Explanations

    North America and regions

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

    The neuron detects mentions of geographic regions or place names (e.g. “North America,” “South America,” “North Shore Drive”).

    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
    {
    -1.48
     obuv
    -1.17
    noah
    -1.16
    jaket
    -1.13
    に来て
    -1.12
    february
    -1.11
    褔
    -1.10
     błę
    -1.09
    eater
    -1.09
     inférieur
    -1.09
    POSITIVE LOGITS
    Zubereitung
    1.18
    
    1.17
     \"
    1.16
    に関しては
    1.11
     квартира
    1.09
    o
    1.09
    坦克
    1.06
     minuten
    1.02
    +}\
    1.02
    桌子
    1.02
    Activations Density 0.043%

    No Known Activations