© 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. 41679
    Prev
    Next
    INDEX
    Explanations

    medical conditions and pathologies

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

    terms related to medical conditions, diseases, or health issues.

    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
    ਞ
    -1.52
     唯美
    -1.48
     the
    -1.43
     perdu
    -1.42
    ."
    -1.40
     of
    -1.38
     科技
    -1.38
    return
    -1.30
     maje
    -1.30
    क्षक
    -1.29
    POSITIVE LOGITS
     such
    1.80
     =
    1.51
     illnesses
    1.30
     mengurangi
    1.30
     svårt
    1.30
     szczeg
    1.30
     that
    1.27
     också
    1.27
     gerekiyor
    1.23
     desde
    1.23
    Activations Density 0.278%

    No Known Activations