© 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. 3900
    Prev
    Next
    INDEX
    Explanations

    name following `if __name__ == '__main__':`

    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
     ל
    2.08
     ن
    1.93
     用于
    1.92
     ر
    1.89
     ت
    1.89
     פ
    1.86
     تم
    1.85
     ג
    1.84
     בי
    1.83
    ⎠
    1.83
    POSITIVE LOGITS
     ondernem
    1.63
    ulla
    1.63
    だから
    1.60
     avrebbe
    1.58
     könnt
    1.58
    ähän
    1.54
     sarebbe
    1.53
    alui
    1.51
     apunta
    1.51
     sarebbero
    1.51
    Activations Density 0.031%

    No Known Activations