© 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. 70153
    Prev
    Next
    INDEX
    Explanations

    medical symptoms and abbreviations

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

    abbreviations and technical codes

    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
     americ
    0.96
    า
    0.91
     aastal
    0.89
    ות
    0.83
    รายงาน
    0.82
     assumptive
    0.80
    ่า
    0.80
     aves
    0.79
     distrito
    0.79
    iyo
    0.78
    POSITIVE LOGITS
     on
    1.15
    t
    1.11
    ني
    1.04
    أ
    0.92
    p
    0.92
    c
    0.90
    ك
    0.90
    ри
    0.89
    There
    0.89
    ро
    0.86
    Activations Density 2.610%

    No Known Activations