© 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. 22-GEMMASCOPE-RES-131K
    4. 35969
    Prev
    Next
    INDEX
    Explanations

    skin, aging, and treatments

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

    content related to skin conditions, beauty treatments, and general health advice.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates strongly on technical or scientific vocabulary—especially dermatology-related terms like intrinsic/extrinsic factors, UV exposure, climates, and other specialized skin-care jargon.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ּוֹ
    -1.58
    וּ
    -1.52
    民众
    -1.50
     vinaigre
    -1.37
     السياس
    -1.28
    :
    -1.27
    ִּ
    -1.24
     меда
    -1.21
     الحكومة
    -1.20
    就可以了
    -1.20
    POSITIVE LOGITS
    ׇ
    1.83
     ویتامین
    1.81
     сахара
    1.71
     your
    1.62
     الشاشة
    1.52
     cukru
    1.52
    ֺ
    1.46
     botanique
    1.43
     प्रोड
    1.40
     kanad
    1.40
    Activations Density 0.057%

    No Known Activations