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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7979
    Prev
    Next
    INDEX
    Explanations

    pathology and damage

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

    pathology, disease progression, and chronic 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
    绦
    0.43
     récord
    0.42
    छोटी
    0.42
     неожидан
    0.42
     Neurology
    0.41
    Unexpected
    0.40
    襁
    0.40
    زاب
    0.39
     unexpected
    0.39
    㕫
    0.39
    POSITIVE LOGITS
     pathogenesis
    1.24
     pathologic
    1.13
     pathophysiology
    1.13
     pathological
    1.12
     pathophys
    1.12
     fibrosis
    1.09
     pathology
    1.05
     degeneration
    1.05
     damage
    1.02
     necrosis
    0.99
    Activations Density 0.070%

    No Known Activations