© 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. 113339
    Prev
    Next
    INDEX
    Explanations

    medical and research institutions

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

    names of medical institutions, hospitals, and research centers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects mentions of proper names of medical or research institutions (e.g., cancer centers, university medical schools).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    mps
    -1.48
     бъдат
    -1.42
    ౮
    -1.40
    !!!!!!!
    -1.34
    ౭
    -1.34
    !!!!!!
    -1.34
    魠
    -1.34
    ౬
    -1.32
     gunakan
    -1.31
    嘚
    -1.30
    POSITIVE LOGITS
     būs
    1.27
     Pyram
    1.23
    SARAH
    1.23
    ၆
    1.23
     Absorb
    1.23
     such
    1.23
     Extracts
    1.21
     fusca
    1.20
    Bises
    1.20
    ↵↵
    1.20
    Activations Density 0.034%

    No Known Activations