© 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. 10-GEMMASCOPE-RES-131K
    7. 41473
    Prev
    Next
    INDEX
    Explanations

    herbal remedies and supplements

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

    words related to herbal medicine, supplements, and traditional remedies.

    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
     on
    -1.64
     one
    -1.60
     three
    -1.42
     zü
    -1.41
     this
    -1.41
     two
    -1.35
    For
    -1.34
    ݮ
    -1.32
    镑
    -1.30
     an
    -1.30
    POSITIVE LOGITS
     człowie
    1.48
     remarkably
    1.45
     มัน
    1.43
     ayur
    1.41
     herhangi
    1.41
    茈
    1.35
     تمامی
    1.34
     入れ
    1.34
    tım
    1.33
     wasn
    1.32
    Activations Density 0.043%

    No Known Activations