© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 57861
    Prev
    Next
    INDEX
    Explanations

    liver and hepatic conditions

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

    liver disease and function

    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_31_width_262k_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
     Vail
    0.58
     Wiltshire
    0.47
     conducteur
    0.47
    尧
    0.47
     latéral
    0.47
     présent
    0.47
    涿
    0.47
     Boise
    0.46
     montagne
    0.46
     déterminé
    0.45
    POSITIVE LOGITS
     hepatic
    1.33
     hepatocytes
    1.27
    肝
    1.26
     liver
    1.24
     hepat
    1.23
     hepatocellular
    1.17
    hepatic
    1.17
     Liver
    1.16
    hepat
    1.15
     livers
    1.14
    Activations Density 0.073%

    No Known Activations