© 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. 6867
    Prev
    Next
    INDEX
    Explanations

    on your mind

    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
    Not in Any Lists

    No Comments

    Negative Logits
     CQG
    1.00
     cump
    0.97
     六
    0.96
     Thur
    0.93
     Hsu
    0.92
     UTM
    0.92
     exceptions
    0.92
     Platts
    0.91
     plaintiff
    0.90
    羿
    0.90
    POSITIVE LOGITS
    ზი
    0.90
    ubin
    0.87
    zim
    0.81
     jana
    0.79
    <0xB2>
    0.77
    न्दा
    0.77
    zad
    0.77
    สาร
    0.76
    zeppelin
    0.75
     তবু
    0.75
    Activations Density 0.095%

    No Known Activations