© 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. 6568
    Prev
    Next
    INDEX
    Explanations

    if `__main__` block

    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
     -=
    1.01
    விய
    0.85
     வில்
    0.85
     |=
    0.83
     ভ
    0.83
     サイド
    0.83
     הת
    0.82
     х
    0.82
    ricao
    0.81
     Term
    0.80
    POSITIVE LOGITS
    ideal
    1.15
    newInstance
    1.14
     specially
    1.08
     idéale
    1.07
     ideal
    1.06
     ideales
    1.05
    enclose
    1.04
     ideale
    1.02
    理想
    1.01
     perfekte
    1.00
    Activations Density 0.005%

    No Known Activations