© 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. 8026
    Prev
    Next
    INDEX
    Explanations

    bars and pubs

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

    The neuron detects mentions of nightlife and drinking establishments (bars, pubs, clubs, 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
    ungkan
    -0.90
    cía
    -0.86
     farmaco
    -0.79
    배
    -0.77
    zada
    -0.76
     olor
    -0.75
    loem
    -0.75
     případ
    -0.74
     арти
    -0.73
    kser
    -0.73
    POSITIVE LOGITS
     bars
    2.89
     bar
    2.73
     pub
    2.27
     pubs
    2.17
     tavern
    1.89
     watering
    1.88
     nightclub
    1.85
    bars
    1.83
     Bars
    1.79
    Bars
    1.77
    Activations Density 0.054%

    No Known Activations