© 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. 31-GEMMASCOPE-2-RES-262K
    7. 2870
    Prev
    Next
    INDEX
    Explanations

    geographical areas

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Simplify
    0.31
     Boolean
    0.31
     Realm
    0.31
     Configure
    0.30
     Reasoning
    0.30
     x
    0.30
     System
    0.30
     Context
    0.29
     Merge
    0.29
     Runtime
    0.29
    POSITIVE LOGITS
    지역
    0.41
    地域の
    0.33
     місце
    0.32
     местные
    0.32
     ও
    0.31
    地区
    0.31
     где
    0.30
     지역
    0.30
     города
    0.30
    elijke
    0.30
    Activations Density 0.180%

    No Known Activations