© 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. 178224
    Prev
    Next
    INDEX
    Explanations

    early time references

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

    foreign and common words

    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
     môi
    0.52
    흄
    0.52
    ະຍ
    0.49
     实现
    0.46
    เที่ยว
    0.46
    лимпий
    0.46
     재생
    0.45
    NIH
    0.45
    
    0.45
     teamwork
    0.45
    POSITIVE LOGITS
    в
    0.50
    चलिए
    0.46
     inklusive
    0.45
     Rotating
    0.44
    affle
    0.43
    lets
    0.43
    has
    0.42
    जगी
    0.42
    š
    0.42
     Alert
    0.42
    Activations Density 0.000%

    No Known Activations