© 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. 62630
    Prev
    Next
    INDEX
    Explanations

    European organizations, conventions, and events

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

    The neuron strongly activates on occurrences of “European” (and related capitalized references to European entities).

    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
    ismes
    -0.80
    getContentPane
    -0.77
    OnTop
    -0.73
    FILENAME
    -0.68
    Scissors
    -0.68
    身份证
    -0.68
    collected
    -0.67
    귓
    -0.67
    パワ
    -0.67
    📘
    -0.66
    POSITIVE LOGITS
     European
    2.94
    European
    2.64
     european
    2.03
    european
    1.84
     европей
    1.83
     Europeans
    1.83
     EUROPEAN
    1.83
     européen
    1.81
    EUROPEAN
    1.80
     europeo
    1.74
    Activations Density 0.031%

    No Known Activations