© 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. 56925
    Prev
    Next
    INDEX
    Explanations

    Siberia and Russian geography

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

    The neuron strongly activates on numeric tokens—years, measurements, quantities, coordinates, and similar digit sequences.

    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
    推荐阅读
    -0.77
    ཕ
    -0.73
    *~*~
    -0.71
     Carri
    -0.70
     susun
    -0.70
    thio
    -0.69
    Merhaba
    -0.68
     Wilmington
    -0.67
     ろ
    -0.66
     shout
    -0.66
    POSITIVE LOGITS
     Siberia
    1.36
     Mongolia
    1.03
     Yak
    1.01
     Siberian
    1.01
    ркут
    0.92
    Yak
    0.91
     Schweitzer
    0.89
     Bury
    0.88
    Si
    0.88
     китай
    0.86
    Activations Density 0.028%

    No Known Activations