© 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. 40-GEMMASCOPE-2-RES-262K
    7. 24765
    Prev
    Next
    INDEX
    Explanations

    detecting specific medical terms or substances

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     oftentimes
    0.78
     și
    0.72
    iliency
    0.72
     skyrocketed
    0.70
     skyrocketing
    0.70
     resiliency
    0.68
     whatnot
    0.66
     ș
    0.66
     subpar
    0.65
     grayish
    0.64
    POSITIVE LOGITS
     Whilst
    1.30
    Whilst
    1.24
     whilst
    1.22
     optimise
    1.00
     recognise
    0.96
     recognised
    0.95
     recognises
    0.92
     anaemia
    0.91
     centre
    0.90
     licences
    0.89
    Activations Density 0.006%

    No Known Activations