© 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. 31-GEMMASCOPE-2-RES-262K
    7. 35905
    Prev
    Next
    INDEX
    Explanations

    sick, sickness, illness

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

    feeling sick or unwell

    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_31_width_262k_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
    tı
    0.77
     glTexParameteri
    0.64
    톄
    0.63
     ساي
    0.62
    <unused19>
    0.61
     زیرمه
    0.61
    𓏧
    0.61
    戙
    0.60
     стрельца
    0.59
     hong
    0.57
    POSITIVE LOGITS
     sick
    1.18
    sick
    1.13
     Sick
    1.05
     sickness
    1.04
     बीमार
    1.02
    Sick
    0.99
     बीमारी
    0.95
    病
    0.92
     illness
    0.90
     illnesses
    0.87
    Activations Density 0.024%

    No Known Activations