© 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. 84587
    Prev
    Next
    INDEX
    Explanations

    Olympic cross-country skiers

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

    This neuron activates on tokens that appear in structured metadata sections—like infobox fields, taxobox entries, or category/template lines—rather than in the article’s normal prose.

    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
    救命
    -0.79
     хватает
    -0.73
    ladimir
    -0.73
     обли
    -0.71
     gladness
    -0.70
    するので
    -0.69
     Grande
    -0.68
     konkrét
    -0.68
     ministro
    -0.66
    してます
    -0.66
    POSITIVE LOGITS
     esperti
    0.89
     薬
    0.85
     stdClass
    0.84
    menin
    0.83
     لق
    0.82
    fering
    0.81
    要有
    0.80
     које
    0.80
    mitted
    0.80
    听
    0.80
    Activations Density 0.002%

    No Known Activations