© 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. 122109
    Prev
    Next
    INDEX
    Explanations

    medical and health terms

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

    generator producing data

    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
    RACT
    0.44
     Genomics
    0.44
     Mercantile
    0.43
     Megh
    0.43
     Rais
    0.42
     Ferry
    0.42
    म
    0.42
     Compre
    0.42
    қ
    0.42
    +[
    0.41
    POSITIVE LOGITS
     ہو۔
    0.48
     செய்தால்
    0.46
     അഭിപ്
    0.46
     swayed
    0.46
     वैलेंट
    0.46
     siano
    0.46
     புல
    0.45
     ischemia
    0.45
     awọn
    0.44
     rozpoczę
    0.44
    Activations Density 0.001%

    No Known Activations