© 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. 10-GEMMASCOPE-RES-131K
    7. 1663
    Prev
    Next
    INDEX
    Explanations

    coffee and coffee shops

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

    The main thing this neuron does is detect references to coffee and related brand or product names (e.g., Dunkin’, mocha, joe, barista).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     proposto
    -1.36
     deiner
    -1.36
    禔
    -1.34
    Producción
    -1.33
    comuna
    -1.32
    zipCode
    -1.31
    性を
    -1.26
     disponível
    -1.26
     färg
    -1.26
    postalCode
    -1.24
    POSITIVE LOGITS
    Coffee
    1.66
    ☕
    1.55
    coffee
    1.51
    $
    1.50
    ☕️
    1.49
     Coffee
    1.42
     coffee
    1.41
    Only
    1.37
     COFFEE
    1.30
     habang
    1.27
    Activations Density 0.049%

    No Known Activations