© 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. 52089
    Prev
    Next
    INDEX
    Explanations

    wild infections

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

    conversion, excellent, prediction, clinical

    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
     স্টি
    0.49
    🏰
    0.48
    폿
    0.47
    ʰ
    0.46
    🗼
    0.46
     পরিষে
    0.46
     機械
    0.46
     بندر
    0.45
    ൨
    0.45
     ਕੁ
    0.45
    POSITIVE LOGITS
     inflammatory
    0.62
     clinically
    0.60
     infections
    0.59
     encephalitis
    0.59
     antibodies
    0.59
     lactic
    0.58
     hemolytic
    0.58
     lymphocytic
    0.57
     ulcerative
    0.56
     asymptomatic
    0.56
    Activations Density 0.000%

    No Known Activations