© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 110672
    Prev
    Next
    INDEX
    Explanations

    combination with, based on, unique

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

    practicing medicine

    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
    ü
    0.52
    Ü
    0.52
     Ü
    0.48
     hoàn
    0.45
    秋冬
    0.44
     Türkiye
    0.42
    ंबई
    0.42
     República
    0.42
     Noronha
    0.41
     Buenas
    0.41
    POSITIVE LOGITS
    🚜
    0.48
     producteurs
    0.47
    :-)
    0.47
    সাম্প্র
    0.46
     intersections
    0.46
     दुष्प्रभाव
    0.45
    пут
    0.44
    毽
    0.44
    erce
    0.44
     kinases
    0.44
    Activations Density 0.001%

    No Known Activations