© 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. 6707
    Prev
    Next
    INDEX
    Explanations

    fabric types

    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
     straps
    0.99
     strap
    0.92
     fastening
    0.92
     velcro
    0.91
    strap
    0.88
     детали
    0.88
    붙
    0.87
    \}^{
    0.87
    🩹
    0.84
     Velcro
    0.84
    POSITIVE LOGITS
     combed
    0.99
    含量
    0.94
    カウント
    0.93
     superf
    0.91
     Wiltshire
    0.90
     lustre
    0.87
     Bourbon
    0.87
     مخلو
    0.86
    頫
    0.85
     Chamb
    0.84
    Activations Density 0.200%

    No Known Activations