© 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. 55825
    Prev
    Next
    INDEX
    Explanations

    occupational workers and employees

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

    The neuron fires on passages describing labor unions or worker organizations—especially where membership numbers, “represents”/“represented,” and other union‐representation details appear.

    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
    Brass
    -0.85
     Macs
    -0.79
     surgeon
    -0.77
     peptide
    -0.77
    inguished
    -0.76
     clientes
    -0.76
     Clients
    -0.75
     Brass
    -0.75
     Kunden
    -0.75
     OFFICER
    -0.75
    POSITIVE LOGITS
     workers
    3.20
     worker
    2.38
    workers
    2.22
    Workers
    2.08
     Workers
    1.96
     trabajadores
    1.73
     WORKERS
    1.58
     working
    1.55
    worker
    1.53
     trabalhadores
    1.50
    Activations Density 0.072%

    No Known Activations