© 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. 13-GEMMASCOPE-2-RES-16K
    7. 12962
    Prev
    Next
    INDEX
    Explanations

    as most things do

    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_13_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
     restful
    1.11
     குடியிருப்ப
    1.10
    eduanya
    1.09
    ersk
    1.05
     occupational
    1.05
    স্থানের
    1.04
    ners
    1.04
     앞
    1.04
    iers
    1.03
    noduch
    1.02
    POSITIVE LOGITS
    شهاد
    1.02
     Index
    1.00
     Histoire
    0.99
    Index
    0.96
     تع
    0.96
     dz
    0.95
     erro
    0.94
     يريد
    0.92
     界
    0.92
     correção
    0.92
    Activations Density 0.019%

    No Known Activations