© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7284
    Prev
    Next
    INDEX
    Explanations

    pants and trousers

    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
     vestido
    1.13
    bridal
    1.04
     Mask
    1.02
    喙
    0.97
    arovski
    0.97
     gown
    0.96
     अग्र
    0.94
     bodice
    0.93
    mask
    0.92
     helm
    0.92
    POSITIVE LOGITS
     legs
    1.05
     colitis
    1.04
     leg
    1.02
     Jeg
    0.96
     jeans
    0.94
    👖
    0.93
     chinos
    0.90
    腿
    0.89
     Cato
    0.88
     पेंट
    0.86
    Activations Density 0.168%

    No Known Activations