© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 127487
    Prev
    Next
    INDEX
    Explanations

    place names

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

    The neuron detects mentions of geographic place names (e.g., cities, counties, neighborhoods).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     into
    -1.83
     a
    -1.76
    which
    -1.66
     his
    -1.61
     in
    -1.60
     by
    -1.55
     not
    -1.55
    Revenir
    -1.50
     The
    -1.50
     $
    -1.48
    POSITIVE LOGITS
    Semua
    1.70
    ofern
    1.67
     Canaria
    1.66
    鶫
    1.64
     этом
    1.62
    
    1.59
    儛
    1.58
    GDPR
    1.55
     congrès
    1.54
    ୫
    1.53
    Activations Density 0.100%

    No Known Activations