© 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. 71261
    Prev
    Next
    INDEX
    Explanations

    surgical operating environment

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

    medical and surgical terminology related to operating rooms and sterile environments.

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

    The neuron primarily picks out terms referring to surgical or operating‐room contexts, especially those emphasizing sterile procedures and equipment.

    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
     in
    -1.30
     Ähnliche
    -1.20
     podríamos
    -1.18
    titud
    -1.16
    useNewUrlParser
    -1.15
     conviene
    -1.14
    DataColumn
    -1.07
     pudieron
    -1.07
    .‏
    -1.05
    selben
    -1.02
    POSITIVE LOGITS
    <strong>
    1.35
    ført
    1.20
    从
    1.15
    蜊
    1.12
     kormány
    1.11
    ngulo
    1.11
    twitter
    1.09
    Mng
    1.09
    úa
    1.09
    xically
    1.09
    Activations Density 0.293%

    No Known Activations