© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73607
    Prev
    Next
    INDEX
    Explanations

    Westminster Abbey, London, College

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

    The neuron strongly activates on mentions of “Westminster” (and related “-minster” place names).

    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
    纐
    -3.02
    
    -3.02
    ‪.‬‬
    -2.84
    歘
    -2.80
     iscri
    -2.75
    祤
    -2.73
     diriger
    -2.72
    
    -2.69
    傒
    -2.67
    genodigd
    -2.63
    POSITIVE LOGITS
    ↵
    3.16
    you
    2.88
     "
    2.81
    )
    2.72
     While
    2.66
    ),
    2.63
    when
    2.61
    ↵↵
    2.59
     <
    2.56
     [
    2.55
    Activations Density 0.002%

    No Known Activations