© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 635
    Prev
    Next
    INDEX
    Explanations

    medical advice decisions related

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Violence
    0.40
    犯罪
    0.36
     زند
    0.35
    Political
    0.35
    étaires
    0.35
     політи
    0.34
    лянчук
    0.34
    Fraud
    0.34
    𠄌
    0.34
    द्योगिक
    0.34
    POSITIVE LOGITS
     clinically
    0.44
     medical
    0.43
     Medical
    0.42
     Ayurvedic
    0.42
     resveratrol
    0.41
     hospital
    0.41
     medicine
    0.41
     medicinal
    0.41
     Ayurveda
    0.40
     patient
    0.40
    Activations Density 0.082%

    No Known Activations