© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78541
    Prev
    Next
    INDEX
    Explanations

    nationalities and countries

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

    The neuron fires on named organizations or group entities—especially sports teams, political parties, leagues, and similar proper-noun labels.

    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
    inerario
    -0.98
    凄く
    -0.95
    brokers
    -0.94
    真正的
    -0.93
    backers
    -0.93
    階の
    -0.90
    具体的な
    -0.89
    人たち
    -0.88
    канчи
    -0.88
    ographers
    -0.88
    POSITIVE LOGITS
     star
    1.24
     phen
    1.17
     monstre
    1.16
     wasn
    1.03
     stun
    1.02
    เจ้า
    1.02
     giant
    1.00
     étui
    1.00
     didn
    0.99
     Congrès
    0.99
    Activations Density 0.054%

    No Known Activations