© 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. 78110
    Prev
    Next
    INDEX
    Explanations

    African currency

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

    contents within parentheses

    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
    热水
    0.49
     жени
    0.47
     infancy
    0.45
     StandardScaler
    0.44
     Fenn
    0.44
    ناوی
    0.44
     hermaph
    0.43
    ⊱
    0.43
     बह
    0.43
     initializer
    0.42
    POSITIVE LOGITS
     Build
    0.48
     Treasures
    0.48
     Officials
    0.46
     blok
    0.45
     দোষ
    0.44
    àn
    0.44
     bisa
    0.44
    رمپ
    0.44
     Watching
    0.43
     Messieurs
    0.43
    Activations Density 0.002%

    No Known Activations