© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48958
    Prev
    Next
    INDEX
    Explanations

    diphtheria, pertussis, influenza

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

    medical and scientific terms related to diseases, bacteria, and vaccines.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Virus
    -0.75
    Ulrich
    -0.74
    ordination
    -0.71
     diminta
    -0.68
    кера
    -0.67
     herpes
    -0.66
     Дже
    -0.66
     cráneo
    -0.65
    ropic
    -0.65
    AppName
    -0.65
    POSITIVE LOGITS
     diphtheria
    1.27
     Pert
    1.07
     Dip
    0.97
     cough
    0.97
     Cough
    0.95
     pert
    0.94
     bạch
    0.91
    pert
    0.89
    Dip
    0.87
    Pert
    0.87
    Activations Density 0.074%

    No Known Activations