© 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. 83093
    Prev
    Next
    INDEX
    Explanations

    Williams brushes

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

    This neuron detects mentions of gig-economy or tech companies (e.g. Deliveroo, Uber) and their business-related terms (startups, funding, employees, per-delivery fees, etc.).

    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
    verein
    -0.77
     grains
    -0.74
    isição
    -0.73
    crição
    -0.73
     ordering
    -0.73
    train
    -0.71
    FFT
    -0.71
     الام
    -0.70
     ligation
    -0.70
     Coimbatore
    -0.70
    POSITIVE LOGITS
     earnings
    1.16
    Earnings
    1.08
     Earnings
    1.05
    earnings
    0.91
     screenshots
    0.89
     deactivated
    0.87
    传说
    0.84
     ऐप
    0.82
    Acceptance
    0.81
     reject
    0.79
    Activations Density 0.006%

    No Known Activations