© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10022
    Prev
    Next
    INDEX
    Explanations

    adverse events and complications

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

    adverse side effects complications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diagnosis
    0.59
    Diagnosis
    0.57
     afflicted
    0.57
     diseased
    0.57
     diagnosing
    0.52
    diagnosis
    0.52
    Diagn
    0.52
    患
    0.52
     Diagnosis
    0.51
     diagnose
    0.49
    POSITIVE LOGITS
     Adverse
    0.76
     adverse
    0.76
     complications
    0.73
     side
    0.66
     complica
    0.64
     complication
    0.64
     Side
    0.62
     complicaciones
    0.62
     eventos
    0.62
     komplik
    0.59
    Activations Density 0.218%

    No Known Activations