© 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. 6567
    Prev
    Next
    INDEX
    Explanations

    online support projects

    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
     शुगर
    1.04
    醪
    0.99
     किरायेदारों
    0.94
     silk
    0.93
     toaster
    0.92
    ทอง
    0.92
     Mortgage
    0.91
     Bakery
    0.91
    巷
    0.90
     आटा
    0.90
    POSITIVE LOGITS
     Wildlife
    2.70
    Wildlife
    2.64
     wildlife
    2.57
     IUCN
    2.43
     naturalist
    2.42
     Zoological
    2.39
     Audubon
    2.38
     Conservation
    2.37
     conservation
    2.34
    Conservation
    2.32
    Activations Density 0.411%

    No Known Activations