© 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. 72508
    Prev
    Next
    INDEX
    Explanations

    double-blind study

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

    The neuron detects the phrase "double blind" (or "double-blind") in scientific study descriptions.

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

    The neuron detects mentions of blinded clinical trials, especially the phrase “double‐blind.”

    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
     both
    -2.11
     different
    -1.87
     kapac
    -1.75
     deudas
    -1.72
     other
    -1.70
     more
    -1.67
     another
    -1.65
     precioso
    -1.56
     Both
    -1.55
     denominado
    -1.48
    POSITIVE LOGITS
     to
    1.79
    tiefel
    1.32
    probieren
    1.30
    ۲۰
    1.24
     všetkých
    1.23
     طف
    1.23
    𝐭
    1.22
     ešte
    1.21
     interesan
    1.19
     wortel
    1.19
    Activations Density 0.109%

    No Known Activations