© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 34590
    Prev
    Next
    INDEX
    Explanations

    osteoarthritis incidence

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

    medical and scientific terminology in healthcare and research contexts.

    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_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
    PRWEB
    -1.01
    VStack
    -1.01
     inferiore
    -0.98
     by
    -0.98
    gardens
    -0.94
    âh
    -0.92
     there
    -0.91
     koła
    -0.89
    ógica
    -0.88
     locali
    -0.88
    POSITIVE LOGITS
     for
    2.83
     для
    1.83
    สำหรับ
    1.70
     of
    1.46
     برای
    1.39
     für
    1.23
     για
    1.19
    для
    1.16
     জন্য
    1.12
    Для
    1.11
    Activations Density 0.334%

    No Known Activations