© 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. 6556
    Prev
    Next
    INDEX
    Explanations

    Human feedback HELP

    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
    irla
    0.89
    lith
    0.85
     이라고
    0.85
    dans
    0.84
    মাত্রা
    0.84
    란
    0.81
    란드
    0.81
    权利
    0.81
    으로서
    0.80
     olarak
    0.80
    POSITIVE LOGITS
     السعود
    1.01
     Sath
    0.99
    填
    0.98
    ेत
    0.97
     उपास
    0.97
    SError
    0.96
    ว้าง
    0.95
    űt
    0.94
    hael
    0.92
    ስተ
    0.92
    Activations Density 0.000%

    No Known Activations