© 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. 10-GEMMASCOPE-RES-131K
    7. 3805
    Prev
    Next
    INDEX
    Explanations

    proper nouns

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

    The neuron fires on capitalized proper names, particularly person names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     halben
    -3.22
    皷
    -2.78
     leeren
    -2.78
     vorigen
    -2.77
     einzigartige
    -2.73
     selben
    -2.59
     falschen
    -2.55
     Zeitraum
    -2.55
     เมื่อ
    -2.53
     kurzen
    -2.50
    POSITIVE LOGITS
    赑
    2.78
    IN
    2.56
     ambayo
    2.52
    na
    2.45
    );
    2.39
    这家
    2.28
    鲧
    2.25
    \
    2.22
     plantes
    2.22
    men
    2.22
    Activations Density 0.020%

    No Known Activations