© 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. 59290
    Prev
    Next
    INDEX
    Explanations

    international organizations and alliances

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

    The neuron fires strongly on names of geopolitical or economic organizations, alliances, blocs, and regions.

    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
     Mannschaft
    -0.93
     族
    -0.93
     the
    -0.90
     dunia
    -0.90
    ところに
    -0.88
     onBind
    -0.85
     uomini
    -0.85
     decreto
    -0.85
     world
    -0.84
    sä
    -0.83
    POSITIVE LOGITS
     countries
    2.17
     member
    2.09
     members
    1.79
    countries
    1.57
     nations
    1.56
     COUNTRIES
    1.53
    member
    1.50
     Member
    1.50
    Member
    1.41
    Countries
    1.41
    Activations Density 0.028%

    No Known Activations