© 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. 45323
    Prev
    Next
    INDEX
    Explanations

    debate

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

    The neuron fires on markers and terminology of formal legislative or parliamentary proceedings (e.g. debate, Lok Sabha, Señor Presidente, cloture).

    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
     drip
    -0.94
    let
    -0.86
    写
    -0.85
    writeValue
    -0.79
    貴
    -0.77
    styleUrls
    -0.76
    WriteBarrier
    -0.75
    าหลี
    -0.75
    寫
    -0.75
     vse
    -0.74
    POSITIVE LOGITS
     debate
    3.25
     Debate
    2.55
     debates
    2.52
    Debate
    2.48
    debate
    2.38
     debated
    2.19
     debating
    2.13
     Debates
    2.03
     debat
    2.03
     débat
    2.02
    Activations Density 0.029%

    No Known Activations