© 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. 115781
    Prev
    Next
    INDEX
    Explanations

    ambassador diplomat envoy

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

    This neuron detects mentions of diplomatic roles and titles (e.g. envoy, ambassador, high commissioner, diplomat).

    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
     international
    -0.85
     zagran
    -0.83
    admin
    -0.82
    Admin
    -0.82
     communication
    -0.82
    海外
    -0.82
     office
    -0.81
     American
    -0.81
    cijas
    -0.80
     Admin
    -0.78
    POSITIVE LOGITS
     Ambassador
    1.73
    Ambassador
    1.61
     ambassador
    1.44
     Ambassadors
    1.23
     ambassadors
    1.18
     embaj
    1.05
     посо
    0.98
    大使
    0.98
     Extraordinary
    0.98
     ambassade
    0.96
    Activations Density 0.013%

    No Known Activations