© 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. 92090
    Prev
    Next
    INDEX
    Explanations

    fashion brands and places

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

    The neuron strongly activates on capitalized proper names—especially brand names or trademarked terms.

    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
    Ironically
    -0.76
     зовут
    -0.76
     evidently
    -0.75
    シフト
    -0.73
    Ethnic
    -0.73
     expiration
    -0.73
    总理
    -0.72
     Ethnic
    -0.70
    巿
    -0.70
    Tribal
    -0.69
    POSITIVE LOGITS
     NY
    0.97
     Coach
    0.92
    enovo
    0.88
    라이
    0.86
    氟
    0.84
     гла
    0.80
    MAY
    0.78
    NYSE
    0.76
    qld
    0.76
    гло
    0.75
    Activations Density 0.015%

    No Known Activations