© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47106
    Prev
    Next
    INDEX
    Explanations

    London locations

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

    The neuron responds strongly to numeric tokens and digit‐based sequences (e.g. street numbers, phone numbers, measurements).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     Greensboro
    -0.93
     Akron
    -0.92
     Davao
    -0.91
     Bistro
    -0.89
     degust
    -0.84
    вная
    -0.82
    ǁ
    -0.82
    ]=(
    -0.82
     valenci
    -0.82
     Schalke
    -0.80
    POSITIVE LOGITS
     London
    2.84
    London
    2.55
    london
    2.14
     london
    2.11
     LONDON
    2.00
     Londres
    1.96
     لندن
    1.85
    LONDON
    1.80
     Лон
    1.77
     Thames
    1.76
    Activations Density 0.150%

    No Known Activations