© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6822
    Prev
    Next
    INDEX
    Explanations

    closing punctuation with quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_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
     confirmation
    0.87
     அச்ச
    0.80
     artı
    0.78
    elasticsearch
    0.77
     формування
    0.77
    nail
    0.77
     underlying
    0.77
    碁
    0.76
     correspondence
    0.76
    緝
    0.76
    POSITIVE LOGITS
     Stadium
    1.16
     stad
    1.15
     stadium
    1.11
     stadion
    1.09
     Stadion
    1.06
     stadiums
    1.05
     ملعب
    1.01
    สนาม
    0.97
     estadio
    0.95
     استاد
    0.94
    Activations Density 0.097%

    No Known Activations