© 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. 38901
    Prev
    Next
    INDEX
    Explanations

    type 2 diabetes

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

    type classifications

    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
     对
    0.51
    ；
    0.51
    大量
    0.48
    可以
    0.47
     ك
    0.45
     即
    0.43
     造
    0.42
    可以直接
    0.42
    ？
    0.42
     אות
    0.41
    POSITIVE LOGITS
    ಕಿ
    0.49
     dyslexia
    0.48
     diminutive
    0.47
    ке
    0.47
     rédu
    0.45
     dissonance
    0.45
    ную
    0.44
     بیاکت
    0.44
     dissenting
    0.44
     Шрифт
    0.44
    Activations Density 0.001%

    No Known Activations