© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58842
    Prev
    Next
    INDEX
    Explanations

    medical supports and devices

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

    medical devices and items used for patient support and immobilization, such as compression stockings, bandages, tourniquets, and casts.

    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
     this
    -1.85
     there
    -1.25
     that
    -1.24
     bienestar
    -1.22
     WHEREAS
    -1.21
    岂
    -1.17
     its
    -1.16
     .
    -1.16
     appla
    -1.16
     Difficulties
    -1.14
    POSITIVE LOGITS
    ۷
    1.41
     innamor
    1.38
    ۹
    1.34
     þe
    1.34
    IALES
    1.33
    nalités
    1.32
     votre
    1.32
    wur
    1.31
    Different
    1.28
    หรือ
    1.28
    Activations Density 0.057%

    No Known Activations