© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99440
    Prev
    Next
    INDEX
    Explanations

    liverpool and surrounding areas

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

    The neuron strongly activates on proper‐noun place names (especially Liverpool wards, streets, and other geographic 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
     Melton
    -0.82
     warszaw
    -0.78
     градусов
    -0.77
     Grig
    -0.75
     peruana
    -0.75
     Ethiopian
    -0.75
    닛
    -0.73
    鄢
    -0.73
    するのが
    -0.72
     Sudbury
    -0.72
    POSITIVE LOGITS
    Liverpool
    2.47
     Liverpool
    2.41
     Merseyside
    2.30
     Mersey
    1.82
     liverpool
    1.75
     Liver
    1.59
    liver
    1.55
    Everton
    1.53
     Anfield
    1.50
     LIVER
    1.45
    Activations Density 0.037%

    No Known Activations