© 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. 226521
    Prev
    Next
    INDEX
    Explanations

    contractor equipment or driver fatigue

    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
    *\
    0.54
    ỵ
    0.51
     química
    0.50
    ビニ
    0.48
    ैल
    0.48
    íny
    0.47
    sthe
    0.47
     INVEST
    0.46
     belles
    0.46
    ᆫ
    0.45
    POSITIVE LOGITS
     konto
    0.47
     dekor
    0.46
     selepas
    0.42
     মাহবুব
    0.42
     Sebelum
    0.41
     Jays
    0.41
    ABA
    0.41
     von
    0.40
    പ്പെട്ട്
    0.40
    ዘጋ
    0.39
    Activations Density 0.001%

    No Known Activations