© 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. 78128
    Prev
    Next
    INDEX
    Explanations

    orders and executive orders

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

    The neuron detects words that name or describe official actions, orders, or status changes (e.g. “lifting,” “closure,” “shutdown,” “evacuation”).

    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
     designates
    -0.75
    ்க்க
    -0.74
     dowry
    -0.72
     Strokes
    -0.71
     Malk
    -0.71
    ringes
    -0.70
     chromos
    -0.69
    litz
    -0.69
    Dolphin
    -0.69
    Matéri
    -0.69
    POSITIVE LOGITS
     orders
    2.09
     order
    1.84
    Order
    1.61
     Orders
    1.61
     stay
    1.61
    Orders
    1.54
     Order
    1.53
    orders
    1.52
     Stay
    1.52
    Stay
    1.45
    Activations Density 0.013%

    No Known Activations