© 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. 6713
    Prev
    Next
    INDEX
    Explanations

    catches errors or health

    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
     Congress
    1.11
     gout
    1.02
     CONGRESS
    1.01
    congress
    0.98
     Congressman
    0.97
     congress
    0.95
    Congress
    0.93
    샘
    0.93
     congressman
    0.92
     constituents
    0.91
    POSITIVE LOGITS
     kriminal
    1.38
    逮捕
    1.35
     saldır
    1.30
     suç
    1.29
    刑事
    1.26
    犯
    1.22
     Policía
    1.20
     policial
    1.20
     polici
    1.20
    ตำรวจ
    1.19
    Activations Density 0.008%

    No Known Activations