© 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. 12868
    Prev
    Next
    INDEX
    Explanations

    Innovation

    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
    nya
    2.88
    ness
    2.48
    skiej
    2.39
    sia
    2.39
    schaft
    2.31
    na
    2.31
    li
    2.27
    ۔
    2.23
    liği
    2.23
    s
    2.21
    POSITIVE LOGITS
     "|
    2.63
     userName
    2.53
    AndKeys
    2.52
    ји
    2.40
    रिय
    2.35
    েজ
    2.35
    煌
    2.34
    
    2.33
     ଶ
    2.31
     Проци
    2.28
    Activations Density 0.050%

    No Known Activations