© 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. 6597
    Prev
    Next
    INDEX
    Explanations

    numbered list opener

    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
     llegada
    0.80
    름
    0.77
    褴
    0.77
    ্লিক
    0.77
     picket
    0.75
    仪式
    0.75
     صف
    0.74
     ld
    0.73
    詼
    0.72
    ället
    0.72
    POSITIVE LOGITS
     Cyg
    0.91
    O
    0.90
    NCH
    0.89
    MoO
    0.88
    ZERO
    0.88
     aet
    0.86
    WAYS
    0.86
    SOCKET
    0.85
     impres
    0.84
    Evolution
    0.83
    Activations Density 0.039%

    No Known Activations