© 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. 199226
    Prev
    Next
    INDEX
    Explanations

    idiom starts like a duck

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

    binding, framework, volume, queue, cosmos

    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
     i
    0.48
     largest
    0.47
     nuevas
    0.46
     sanitize
    0.46
     currentRow
    0.46
     new
    0.45
     highest
    0.45
     Smart
    0.43
     mora
    0.43
     boxes
    0.43
    POSITIVE LOGITS
     Екатери
    0.57
    conto
    0.56
    峭
    0.54
    rennt
    0.50
    szön
    0.50
     Throughout
    0.49
    жении
    0.48
    anhyd
    0.48
    :“
    0.48
    몄
    0.47
    Activations Density 0.000%

    No Known Activations