© 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. 12885
    Prev
    Next
    INDEX
    Explanations

    prevalence and incidence

    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
    liquidacion
    0.63
    لاش
    0.60
     പങ്കെടു
    0.59
     enthusi
    0.58
    নির
    0.58
    揶
    0.58
     মতামত
    0.57
     Quỳnh
    0.57
    貫
    0.57
    ضب
    0.57
    POSITIVE LOGITS
     prevalence
    1.58
     Prevalence
    1.44
     worldwide
    1.39
     incidence
    1.34
     Incidence
    1.26
     preventable
    1.25
     annually
    1.23
     morbidity
    1.23
    每年
    1.23
     epidemiology
    1.19
    Activations Density 0.078%

    No Known Activations