© 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. 10-GEMMASCOPE-RES-131K
    7. 22753
    Prev
    Next
    INDEX
    Explanations

    place names and proper nouns

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

    The neuron detects tokens that are part of proper geographic place names (cities, towns, districts, regions).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     trám
    -1.73
    ㈧
    -1.63
    lerim
    -1.59
    ጺ
    -1.55
    bluza
    -1.55
    皛
    -1.53
    besar
    -1.52
     ",";
    -1.51
     pohod
    -1.50
    好用
    -1.49
    POSITIVE LOGITS
     '
    2.03
    se
    1.71
     иной
    1.66
    é
    1.65
    ti
    1.55
     следующих
    1.55
     o
    1.52
    ty
    1.52
     /
    1.50
    r
    1.50
    Activations Density 0.005%

    No Known Activations