© 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. 2348
    Prev
    Next
    INDEX
    Explanations

    saunas and steam baths

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

    This neuron fires on multiword product or brand names (i.e. sequences of capitalized terms denoting specific equipment or trademarks).

    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
    =".$
    -0.72
     ۱۳
    -0.69
     (!
    -0.69
    WY
    -0.68
     stip
    -0.67
    ә
    -0.67
    leetcode
    -0.65
    Canvas
    -0.65
     Station
    -0.65
    olution
    -0.64
    POSITIVE LOGITS
     sauna
    3.80
     steam
    2.95
     Sauna
    2.56
    steam
    2.36
     Steam
    2.30
    Steam
    2.16
    サウナ
    1.77
     Turkish
    1.60
     steaming
    1.59
     sa
    1.58
    Activations Density 0.028%

    No Known Activations