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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 11900
    Prev
    Next
    INDEX
    Explanations

    European Parliament or Commission

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

    The neuron activates on names of formal political or regulatory bodies (e.g. parliaments, commissions, committees, assemblies) in various languages.

    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
     in
    -1.06
     of
    -1.05
    なんでも
    -0.93
    何でも
    -0.91
     with
    -0.87
    科普
    -0.82
     ecru
    -0.82
     from
    -0.81
    の概要
    -0.81
    timbangkan
    -0.80
    POSITIVE LOGITS
    ฯ
    0.94
    ERP
    0.88
     Chinese
    0.87
    时
    0.85
     Stratford
    0.85
    濱
    0.85
    κέ
    0.85
     الاتحاد
    0.85
    ผู้
    0.84
    aughan
    0.83
    Activations Density 0.011%

    No Known Activations