© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8379
    Prev
    Next
    INDEX
    Explanations

    coronary artery occlusion

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

    arteries, vessels, vascular conditions

    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_53_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
     गोबर
    0.47
    抹茶
    0.42
    浱
    0.42
     refugee
    0.41
     instagram
    0.41
     Refugee
    0.40
    ຜະລ
    0.39
    🇼
    0.39
     Pokemon
    0.39
     pokemon
    0.39
    POSITIVE LOGITS
     arteries
    2.48
     artery
    2.42
     arterial
    2.25
     arter
    2.20
    血管
    2.16
     vessels
    2.11
     Arter
    2.11
     aorta
    2.09
     vascular
    2.08
     vessel
    2.06
    Activations Density 0.099%

    No Known Activations