© 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. 148776
    Prev
    Next
    INDEX
    Explanations

    locations, activities, and groups

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

    US Tax

    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
     =
    0.53
     Interactions
    0.52
     Tested
    0.52
     Hg
    0.48
     Spray
    0.48
     Ig
    0.48
     Drilling
    0.48
     Protective
    0.47
    崙
    0.47
     Skate
    0.47
    POSITIVE LOGITS
     nowych
    0.54
    usetzen
    0.52
     pasukan
    0.52
     nazw
    0.50
     nuevos
    0.50
     জনপ্রিয়
    0.48
     caderno
    0.48
     nuovo
    0.47
     jargon
    0.47
     murderous
    0.47
    Activations Density 0.001%

    No Known Activations