© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10825
    Prev
    Next
    INDEX
    Explanations

    news links

    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
    モノ
    0.74
    ྟ
    0.74
    ﾄ
    0.73
     گم
    0.73
    ﻃ
    0.72
    Θ
    0.70
     బా
    0.70
    ذه
    0.69
     মাধ্যম
    0.69
    печат
    0.69
    POSITIVE LOGITS
     Xie
    0.99
    ানিতে
    0.97
     Holi
    0.97
     የማይ
    0.96
     Nikhil
    0.95
     Virology
    0.94
     wabarakatuh
    0.89
    }-[
    0.89
     llegando
    0.87
    ikiem
    0.86
    Activations Density 0.037%

    No Known Activations