© 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. 48381
    Prev
    Next
    INDEX
    Explanations

    National Assembly, Academy, Incorporated

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

    The neuron fires on tokens that are part of formal organization or institution names (e.g. “National” in “National Assembly” or “National Academy”).

    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
     системы
    -0.87
    Vera
    -0.79
     系统
    -0.77
    System
    -0.77
    系统
    -0.75
     sistema
    -0.73
     системи
    -0.70
     System
    -0.69
     IFT
    -0.69
     Vera
    -0.68
    POSITIVE LOGITS
    grants
    0.76
    dcm
    0.66
     auquel
    0.65
     ملع
    0.65
     type
    0.64
     czo
    0.63
    drav
    0.63
     Type
    0.62
    rischen
    0.62
     creation
    0.61
    Activations Density 0.052%

    No Known Activations