© 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. 90403
    Prev
    Next
    INDEX
    Explanations

    Bristol and associated places

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

    This neuron detects mentions of place names or geographic locations, especially “Bristol.”

    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
    gating
    -0.73
    ַּ
    -0.73
     Opel
    -0.71
    ꯪ
    -0.71
     stored
    -0.71
    submissions
    -0.69
     Shreve
    -0.68
    还可以
    -0.68
     Mahi
    -0.68
     اسپ
    -0.67
    POSITIVE LOGITS
     Bristol
    2.75
    Bristol
    2.58
     Brist
    1.41
    ristol
    1.39
     Gloucestershire
    1.31
    Avon
    1.27
     Avon
    1.23
     Cabot
    1.05
     Somerset
    0.98
     Bath
    0.97
    Activations Density 0.018%

    No Known Activations