© 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
    5. 16-GEMMASCOPE-2-RES-16K
    7. 802
    Prev
    Next
    INDEX
    Explanations

    Dominican Republic and contagious diseases

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

    Dominican Republic, contagious

    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_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    å
    0.52
     moto
    0.51
     hopelessly
    0.51
     pipes
    0.50
     beurre
    0.50
     jails
    0.49
    こと
    0.48
     regulates
    0.48
     piles
    0.47
     overly
    0.47
    POSITIVE LOGITS
    د
    0.66
    instruction
    0.64
    ynamic
    0.59
     Жу
    0.57
    general
    0.57
    dı
    0.57
    sru
    0.57
    sı
    0.57
    s
    0.57
    equivariant
    0.56
    Activations Density 0.001%

    No Known Activations