© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48582
    Prev
    Next
    INDEX
    Explanations

    leaving EU membership

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

    The neuron strongly responds to tokens referring to Britain’s exit from or membership in the European Union (e.g. “leaving,” “withdrawal,” “remain,” “EU,” “single market,” “European Union,” “Article 50”).

    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
    KD
    -0.83
     ผู้
    -0.79
    鞋子
    -0.77
     \,
    -0.75
    nefs
    -0.74
     CASA
    -0.73
     собака
    -0.73
     Dames
    -0.72
    чные
    -0.72
    чных
    -0.72
    POSITIVE LOGITS
     membership
    1.34
    membership
    1.14
     renegoti
    1.08
    exit
    1.05
     exit
    1.02
     EU
    0.98
    Membership
    0.98
     Membership
    0.95
    member
    0.87
     Britain
    0.85
    Activations Density 0.012%

    No Known Activations