© 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. 34-GEMMASCOPE-RES-131K
    7. 73591
    Prev
    Next
    INDEX
    Explanations

    medical operations performed on patients

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

    medical research abstracts, particularly detecting text in scientific papers about patient studies and medical procedures.

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

    The neuron is tuned to pick out numeric and quantitative data (e.g. sample sizes, years, counts, percentages) in clinical‐research text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Истори
    -0.77
     lastik
    -0.77
    photos
    -0.76
    tual
    -0.74
    cock
    -0.73
    anthene
    -0.73
     медици
    -0.73
     Dimen
    -0.72
    ditions
    -0.72
     benthic
    -0.71
    POSITIVE LOGITS
     appointment
    1.14
     precinct
    1.08
     appointments
    1.05
     consultation
    1.04
     consultations
    1.02
     appointed
    1.02
     tactics
    0.99
     ward
    0.93
     appoints
    0.90
     dispensary
    0.89
    Activations Density 0.039%

    No Known Activations