© 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. 41-GEMMASCOPE-2-RES-262K
    7. 26574
    Prev
    Next
    INDEX
    Explanations

    disease and contagion

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    த்தே
    0.44
     액세
    0.42
     accessori
    0.41
    锲
    0.41
     প্ল্যাট
    0.40
     फ्रेम
    0.40
    充电
    0.40
     బంగ
    0.40
    扃
    0.40
    电动
    0.39
    POSITIVE LOGITS
     epidemic
    1.59
     epidemics
    1.52
     outbreaks
    1.49
     outbreak
    1.44
     disease
    1.43
     infection
    1.42
     virus
    1.40
     contagion
    1.36
     infected
    1.33
     infectious
    1.33
    Activations Density 0.005%

    No Known Activations