© 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. 6539
    Prev
    Next
    INDEX
    Explanations

    precedes or follows

    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
    tom
    1.01
     Razor
    1.00
    იდ
    0.99
     doxy
    0.98
    ვ
    0.90
     Depth
    0.89
     march
    0.89
    ձ
    0.89
     Horn
    0.88
     poke
    0.88
    POSITIVE LOGITS
    uali
    1.02
    ujud
    1.00
    arend
    0.99
    aménagement
    0.99
    পূ
    0.99
    लेल्या
    0.98
    enciones
    0.98
     כמ
    0.98
    linde
    0.98
    ینه
    0.96
    Activations Density 0.000%

    No Known Activations