© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 108088
    Prev
    Next
    INDEX
    Explanations

    European Union, spatial distance, tube opening

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

    Duolingo, Compiler Errors, Mouser

    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
    Negative Logits
     egal
    0.57
     A
    0.54
     is
    0.49
     includes
    0.48
     purposes
    0.46
     potentially
    0.46
     അതിന്റെ
    0.46
    ↵↵↵
    0.46
     a
    0.46
     i
    0.45
    POSITIVE LOGITS
    日々
    0.50
    흐
    0.49
     thisTrial
    0.49
    하였다
    0.46
     días
    0.45
     exerting
    0.44
    宀
    0.44
    쥐
    0.43
    печа
    0.43
    இய
    0.43
    Activations Density 0.001%

    No Known Activations