© 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. 82307
    Prev
    Next
    INDEX
    Explanations

    Kentucky and Appalachian regions, coal

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

    The neuron detects named geographic and institutional place names (e.g. towns, counties, states, regions, and similarly formatted proper‐noun locations).

    oai_token-act-pair · o4-miniTriggered 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
    渚
    -0.88
     شہر
    -0.81
     CIE
    -0.81
    vaných
    -0.79
     Copying
    -0.77
     Taur
    -0.76
     jasmine
    -0.76
     Pelican
    -0.75
    北方
    -0.75
    вия
    -0.74
    POSITIVE LOGITS
     Appalachian
    1.61
    Kentucky
    1.49
     mountain
    1.47
     Kentucky
    1.46
     Appalach
    1.46
     coal
    1.45
    mountain
    1.40
    coal
    1.30
    Mountain
    1.30
    Coal
    1.29
    Activations Density 0.022%

    No Known Activations