© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 38196
    Prev
    Next
    INDEX
    Explanations

    lavender

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

    The neuron detects mentions of soothing aromatherapy scents—especially lavender (and related calming ingredients like chamomile, vanilla, essential oils, pillow mists, etc.).

    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
    紅葉
    -0.97
     pumpkin
    -0.85
     tomato
    -0.82
     red
    -0.80
    🍁
    -0.79
    🍂
    -0.77
     Genealogy
    -0.76
     cheese
    -0.75
    Halloween
    -0.75
     đèn
    -0.73
    POSITIVE LOGITS
     Lavender
    1.30
     lavender
    1.27
    Lavender
    1.18
    薰
    1.09
     sachets
    1.06
     fields
    1.04
    lavender
    0.95
     angusti
    0.95
     Fields
    0.91
    buds
    0.90
    Activations Density 0.005%

    No Known Activations