© 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-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5741
    Prev
    Next
    INDEX
    Explanations

    communication and efficiency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     아닌
    0.80
     জীবিত
    0.77
    ärte
    0.75
    ুতের
    0.74
    ():
    0.74
     좌표
    0.73
     아니고
    0.72
     అ
    0.70
     THIRD
    0.70
     조
    0.70
    POSITIVE LOGITS
     dent
    0.79
     Dent
    0.72
     Comunic
    0.70
     comunic
    0.70
    纵
    0.69
     eficiente
    0.65
     fáciles
    0.65
     comunica
    0.65
     Franch
    0.65
     Prior
    0.64
    Activations Density 0.037%

    No Known Activations