© 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. 79237
    Prev
    Next
    INDEX
    Explanations

    communist and marxist politics

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

    The neuron strongly activates on number‐like tokens—years, dates, digits, and other numeric strings.

    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
     芝
    -0.78
     "."
    -0.73
     Familia
    -0.73
     rozwią
    -0.72
    ⅲ
    -0.71
     "_"
    -0.71
     Baylor
    -0.69
    馒头
    -0.69
     psychotherapy
    -0.69
    FORMAT
    -0.68
    POSITIVE LOGITS
     CPI
    1.32
     CPM
    1.28
     Communist
    1.17
     Marxist
    1.16
    CPM
    1.15
     communist
    1.09
    CPI
    1.07
    Communist
    1.05
     Left
    1.02
     Comrade
    1.01
    Activations Density 0.053%

    No Known Activations