© 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. 23832
    Prev
    Next
    INDEX
    Explanations

    skilled trades and artisans

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

    The neuron responds to content‐bearing word pieces (especially nouns, proper names, adjectives, and other multisyllabic roots), distinguishing them from grammar or function words.

    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
     MANAGEMENT
    -0.98
    ικού
    -0.91
     novels
    -0.90
     двигатель
    -0.89
    ocrine
    -0.88
    Management
    -0.88
    Staff
    -0.86
    Photography
    -0.85
     clinical
    -0.85
     PHOTOGRAPHY
    -0.85
    POSITIVE LOGITS
     craftsman
    2.61
     craftsmen
    2.53
     craftsmanship
    2.53
     artisans
    2.39
     craft
    2.38
     skilled
    2.38
     crafts
    2.34
     workshop
    2.25
     workshops
    2.08
     artisan
    2.06
    Activations Density 0.065%

    No Known Activations