© 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. 10-GEMMASCOPE-RES-131K
    4. 1846
    Prev
    Next
    INDEX
    Explanations

    dermatology, Cathy

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

    names or references to "Cathy" and dermatology-related terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     جديدة
    -3.05
    ᕱ
    -2.83
    檍
    -2.77
    柃
    -2.72
    錀
    -2.67
    鸰
    -2.64
     福袋
    -2.61
    嫘
    -2.58
    烁
    -2.55
    笕
    -2.55
    POSITIVE LOGITS
    0
    3.33
    1
    3.30
    [
    3.13
    >
    2.88
     They
    2.58
     Maintaining
    2.50
     Achieving
    2.47
    y
    2.47
     Featuring
    2.39
     captivated
    2.39
    Activations Density 0.002%

    No Known Activations