© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12948
    Prev
    Next
    INDEX
    Explanations

    locations, places, and points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     grootste
    0.40
    تب
    0.37
    ச்சார
    0.37
    误
    0.37
    誤
    0.37
     saat
    0.36
    醍
    0.35
     contenido
    0.35
     Kategorie
    0.35
     job
    0.35
    POSITIVE LOGITS
    locations
    0.79
     locations
    0.76
    場所
    0.68
    곳
    0.68
    에서의
    0.66
     места
    0.66
    স্থল
    0.65
    where
    0.64
     곳
    0.64
     Locations
    0.64
    Activations Density 0.028%

    No Known Activations