© 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. 83351
    Prev
    Next
    INDEX
    Explanations

    placebo-controlled studies

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

    The neuron detects medical research study terms, specifically "placebo-controlled" in clinical trial descriptions.

    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_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
    Quote
    -0.77
     Quote
    -0.72
     super
    -0.66
    Neu
    -0.65
    GridQubit
    -0.65
    [:
    -0.62
    неве
    -0.62
    umburg
    -0.61
     殿
    -0.60
     quote
    -0.60
    POSITIVE LOGITS
    ⌂
    0.76
    carpet
    0.76
    estaw
    0.75
    Debra
    0.73
     grupy
    0.71
    pne
    0.71
    mici
    0.70
    veillance
    0.69
    דות
    0.69
     bristle
    0.69
    Activations Density 0.052%

    No Known Activations