© 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. 6834
    Prev
    Next
    INDEX
    Explanations

    CSS properties and selectors

    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
    Not in Any Lists

    No Comments

    Negative Logits
     vertebrae
    1.45
     vertebra
    1.32
     Spine
    1.16
    脊
    1.16
    Neck
    1.15
     spine
    1.13
    郧
    1.13
     गर्दन
    1.13
     Neck
    1.13
    ネック
    1.12
    POSITIVE LOGITS
     Kendrick
    1.05
    姮
    0.94
     knee
    0.94
     creatinine
    0.93
     Jama
    0.92
     Reign
    0.91
     Koc
    0.91
     knees
    0.90
     Moder
    0.87
     Blazers
    0.87
    Activations Density 0.158%

    No Known Activations