© 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. 10673
    Prev
    Next
    INDEX
    Explanations

    kidney diseases and conditions

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

    kidney and renal 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_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
     théâtre
    0.63
    股价
    0.56
    诡
    0.55
    员工
    0.54
    广大
    0.54
    🎭
    0.54
    🚇
    0.53
     Theatre
    0.52
     میدان
    0.52
    伟大
    0.52
    POSITIVE LOGITS
     renal
    1.45
     kidney
    1.41
     neph
    1.35
     proteinuria
    1.35
     kidneys
    1.34
     glomerular
    1.28
    腎
    1.27
     urinary
    1.25
     Renal
    1.13
     किडनी
    1.11
    Activations Density 0.045%

    No Known Activations