© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8246
    Prev
    Next
    INDEX
    Explanations

    Swat Valley geographical locations

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

    bytes decode utf-8

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    يران
    0.45
     বেলু
    0.45
    測定
    0.44
    繪
    0.43
    ਭ
    0.42
     Measurement
    0.41
     Busch
    0.41
    計測
    0.40
    ুয়ারি
    0.40
    浥
    0.40
    POSITIVE LOGITS
     think
    0.51
     Think
    0.48
    addons
    0.48
     curled
    0.46
     addons
    0.45
    think
    0.44
     deng
    0.44
     muit
    0.43
     jumps
    0.42
    wap
    0.42
    Activations Density 0.013%

    No Known Activations