© 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. 82808
    Prev
    Next
    INDEX
    Explanations

    Cambridge and Anglia

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

    The neuron fires on mentions of geographic place names (e.g. “Sandy,” “Bedfordshire,” “Cambridge,” etc.).

    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
    drawText
    -0.75
     RTA
    -0.74
     Sligo
    -0.73
     instantly
    -0.72
     civilized
    -0.72
    聞き
    -0.70
     SDS
    -0.70
     Malaga
    -0.69
     initialize
    -0.68
     y
    -0.68
    POSITIVE LOGITS
     Cambridge
    1.95
    Cambridge
    1.80
     Camb
    1.50
    Camb
    1.42
    camb
    1.28
     camb
    1.28
     Suffolk
    1.21
    ridgeshire
    0.98
     Anglia
    0.94
     fen
    0.94
    Activations Density 0.029%

    No Known Activations