© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 12729
    Prev
    Next
    INDEX
    Explanations

    antigens and allergens

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     cardiomyocyte
    0.67
     cardiomyocytes
    0.67
    FileOutputStream
    0.59
     warfarin
    0.58
    玉
    0.57
     xylem
    0.56
     fibroblast
    0.55
    outFile
    0.55
     neutron
    0.55
    黙
    0.55
    POSITIVE LOGITS
     antigen
    2.30
     Antigen
    2.22
     antigens
    2.19
     antigenic
    1.95
     epitope
    1.68
     epitopes
    1.68
     HLA
    1.42
     MHC
    1.32
    HLA
    1.26
     allergen
    1.25
    Activations Density 0.046%

    No Known Activations