© 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. 82760
    Prev
    Next
    INDEX
    Explanations

    coffee shops and cafes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    dinner
    -1.29
     dinner
    -1.23
    Dinner
    -1.12
     DINNER
    -1.01
     Dinner
    -1.00
     steak
    -0.99
    steak
    -0.98
    Cocktail
    -0.96
    Steak
    -0.94
     night
    -0.94
    POSITIVE LOGITS
     cafe
    2.52
     café
    2.42
     coffee
    2.38
     cafes
    1.95
     Cafe
    1.93
     Café
    1.91
     barista
    1.90
    cafe
    1.88
     Coffee
    1.87
    Coffee
    1.82
    Activations Density 0.018%

    No Known Activations