© 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. 2617
    Prev
    Next
    INDEX
    Explanations

    hot drinks

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

    This neuron fires on short verb-plus-article noun phrases—i.e. patterns like “waiting to get a …,” “send back the …,” or in Spanish “Quiero un vaso de ….”

    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
     raste
    -0.73
    uguetes
    -0.73
     暖
    -0.72
    住院
    -0.71
    钢琴
    -0.71
     uncontrol
    -0.70
     Miley
    -0.70
     Baker
    -0.70
     volatility
    -0.69
     بندی
    -0.69
    POSITIVE LOGITS
     drinks
    2.45
     drink
    1.89
     Drinks
    1.59
     bebidas
    1.57
     beverages
    1.54
    drinks
    1.54
     beverage
    1.53
     water
    1.47
    Drink
    1.44
    Drinks
    1.38
    Activations Density 0.003%

    No Known Activations