© 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. 7-GEMMASCOPE-2-RES-16K
    7. 3953
    Prev
    Next
    INDEX
    Explanations

    embedded systems

    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_7_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
    ంట
    2.13
    ंतिक
    2.05
    有人
    2.03
    い
    2.00
    urel
    1.98
    ლი
    1.98
    嵘
    1.95
    ਾਵ
    1.95
    vali
    1.95
     Accident
    1.93
    POSITIVE LOGITS
    zta
    2.34
    淉
    2.26
    ွား
    2.17
    creen
    2.16
    nare
    2.13
    wiata
    2.11
    (&
    2.10
    ্থ
    2.10
    ্ধ
    2.09
    ípios
    2.09
    Activations Density 0.048%

    No Known Activations