© 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. 102924
    Prev
    Next
    INDEX
    Explanations

    types of water

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

    The neuron fires most strongly on mentions of water and bottled (or soft) drinks—i.e. beverage references.

    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
    brei
    -0.82
    海
    -0.80
    Udp
    -0.76
    炬
    -0.72
    奶
    -0.71
    畑
    -0.69
    ௌ
    -0.69
    ̤
    -0.68
     Grease
    -0.68
     суп
    -0.67
    POSITIVE LOGITS
     bottled
    2.39
     filtered
    2.06
    filtered
    1.77
     water
    1.77
     Filtered
    1.70
     sparkling
    1.68
    Filtered
    1.67
     mineral
    1.63
     purified
    1.58
     минера
    1.48
    Activations Density 0.018%

    No Known Activations