© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103636
    Prev
    Next
    INDEX
    Explanations

    business and trade keywords

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

    The neuron is highly sensitive to formal government decree language announcing policy changes—especially terms around “relaxation of lockdown” and free movement orders.

    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
     chest
    -0.78
     tons
    -0.75
    naya
    -0.75
     współ
    -0.74
    adone
    -0.73
    Thresh
    -0.71
     ஊ
    -0.71
     Africans
    -0.71
    дравству
    -0.71
    paedia
    -0.70
    POSITIVE LOGITS
     business
    0.93
     comerciantes
    0.87
     Hawking
    0.87
     التجار
    0.86
     traders
    0.84
    畅
    0.83
    authorization
    0.82
     commercial
    0.79
     activities
    0.78
    🥓
    0.76
    Activations Density 0.009%

    No Known Activations