© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84756
    Prev
    Next
    INDEX
    Explanations

    informed consent

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

    This neuron detects mentions of the informed‐consent process—words describing patients providing written informed consent in a study or protocol.

    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
     RECOGN
    -0.85
     RÉ
    -0.78
     Backbone
    -0.75
    🔷
    -0.73
    Passer
    -0.72
    стреча
    -0.71
    developing
    -0.71
    gong
    -0.71
     fratern
    -0.71
    izm
    -0.70
    POSITIVE LOGITS
     consent
    4.59
    consent
    3.33
     Consent
    3.28
    Consent
    3.11
     consentimiento
    2.47
     consents
    2.42
     consented
    2.36
    同意
    2.16
     consentement
    2.11
     consentimento
    2.05
    Activations Density 0.058%

    No Known Activations