© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91935
    Prev
    Next
    INDEX
    Explanations

    nightclub

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

    The neuron detects mentions of club‐related nightlife terms (e.g. “club,” “clubbing,” “nightclub,” “nightlife”).

    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
     homeschool
    -0.91
    ूप
    -0.88
     cafés
    -0.87
    lunch
    -0.85
    Lunch
    -0.84
    DataSetChanged
    -0.83
    είο
    -0.79
    ksiyon
    -0.79
     webinar
    -0.79
    午餐
    -0.79
    POSITIVE LOGITS
     nightclub
    3.27
     club
    2.78
     clubs
    2.48
     nightlife
    2.42
    club
    2.14
    Club
    2.00
     klub
    1.98
    clubs
    1.90
     CLUB
    1.88
     Club
    1.86
    Activations Density 0.066%

    No Known Activations