© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63974
    Prev
    Next
    INDEX
    Explanations

    waiters, waitresses, butlers, bellhops

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

    The neuron fires on mentions of hospitality or service‐industry roles (e.g. waiter, bellboy, sommelier, wine writer, camarera).

    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
     constructors
    -0.78
     EW
    -0.75
     constructor
    -0.74
     डॉ
    -0.74
    火力
    -0.73
    XmlIgnore
    -0.71
     компью
    -0.70
     processor
    -0.68
     investigators
    -0.68
     developer
    -0.68
    POSITIVE LOGITS
     waiters
    2.53
     waiter
    2.48
    waiter
    1.85
     serving
    1.81
    Waiter
    1.58
     servers
    1.55
     Servers
    1.53
     Serving
    1.52
    服务
    1.50
    serving
    1.47
    Activations Density 0.031%

    No Known Activations