© 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. 6545
    Prev
    Next
    INDEX
    Explanations

    items being carried or owned

    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
    ڑک
    0.86
     wristwatch
    0.84
    ematic
    0.80
     websites
    0.79
    咀
    0.79
    Knife
    0.77
    桌
    0.77
    錶
    0.72
     website
    0.71
     அமைப்பு
    0.71
    POSITIVE LOGITS
     load
    1.47
     groceries
    1.44
     payload
    1.44
    Load
    1.42
    load
    1.38
     yük
    1.37
     carga
    1.37
     payloads
    1.36
     beban
    1.35
     Load
    1.32
    Activations Density 0.291%

    No Known Activations