© 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. 73468
    Prev
    Next
    INDEX
    Explanations

    geopolitical actions and international relations

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

    The neuron detects language about geopolitical strategy and high‐level strategic planning or maneuvering.

    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
     umane
    -1.19
    Ϝ
    -1.13
     ferie
    -1.13
    ❃
    -1.11
    คน
    -1.11
     collega
    -1.10
     souvent
    -1.09
     relentless
    -1.08
    Atsauces
    -1.05
     litri
    -1.05
    POSITIVE LOGITS
     diplomatic
    1.74
     diplomats
    1.47
     bilateral
    1.42
     countries
    1.34
     Washington
    1.32
    民众
    1.27
     geopolitical
    1.26
    ilateral
    1.24
     NATO
    1.24
     international
    1.24
    Activations Density 0.091%

    No Known Activations