© 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. 22-GEMMASCOPE-RES-131K
    7. 13667
    Prev
    Next
    INDEX
    Explanations

    country-to-country cooperation

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

    The neuron strongly activates on mentions of country names or national-to-national relationships.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    verkauf
    -1.33
     الشاشة
    -1.22
     reputa
    -1.20
     你
    -1.20
    isling
    -1.20
     Finlandia
    -1.19
     Fungsi
    -1.18
     precau
    -1.18
     жовтня
    -1.17
    🛐
    -1.16
    POSITIVE LOGITS
    之事
    1.33
    erobic
    1.24
     counterpart
    1.22
     reciproc
    1.16
     reciprocal
    1.16
    academia
    1.15
     mutual
    1.13
    窗外
    1.13
    身子
    1.13
     interest
    1.11
    Activations Density 0.030%

    No Known Activations