© 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. 6599
    Prev
    Next
    INDEX
    Explanations

    `px` after start token

    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
    ಧಾನ
    0.98
    onya
    0.91
     znalaz
    0.89
     Monde
    0.89
    ሖ
    0.89
    ائص
    0.88
     নগর
    0.88
    omba
    0.87
    меры
    0.86
     মসজিদে
    0.85
    POSITIVE LOGITS
     #
    0.87
    事的
    0.82
    ñana
    0.81
    /*!
    0.81
     aspirant
    0.77
     lofty
    0.76
     <!--
    0.76
    graphicx
    0.74
     ▼
    0.73
    /*
    0.73
    Activations Density 0.012%

    No Known Activations