© 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. 1135
    Prev
    Next
    INDEX
    Explanations

    illness and medical conditions

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

    medical conditions and decline

    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
     REPRESENT
    0.46
     значение
    0.46
    我們可以
    0.45
     เลือก
    0.45
     AVAILABLE
    0.45
     BOOLE
    0.44
    觀
    0.44
     MARKET
    0.43
    客
    0.43
     ഓഫ
    0.42
    POSITIVE LOGITS
     malattia
    0.93
     بیماری
    0.91
    病情
    0.91
     medically
    0.90
     diagnosed
    0.88
     penyakit
    0.88
     pancreatitis
    0.88
     pneumonia
    0.87
     lymphoma
    0.86
     illness
    0.86
    Activations Density 0.391%

    No Known Activations