© 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. 30129
    Prev
    Next
    INDEX
    Explanations

    swiss and Switzerland

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

    The neuron fires on occurrences of “Swiss” (and related form “Switzerland”), i.e. it detects references to Swiss 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
    醸
    -0.80
    悩む
    -0.79
     juxtaposition
    -0.77
    ガキ
    -0.76
     pájaro
    -0.76
     وين
    -0.76
     pequena
    -0.75
    8
    -0.75
    一起去
    -0.73
    utkan
    -0.73
    POSITIVE LOGITS
     Swiss
    1.27
    Swiss
    1.25
     Switzerland
    1.02
    瑞士
    0.99
    🇨
    0.95
    swiss
    0.92
    Borg
    0.92
     army
    0.92
     swiss
    0.91
     Alps
    0.91
    Activations Density 0.008%

    No Known Activations