© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1452
    Prev
    Next
    INDEX
    Explanations

    digital art creation or exhibits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     softball
    0.69
    бре
    0.61
     transistors
    0.60
     pés
    0.60
    Agr
    0.57
     చంద్ర
    0.57
    জনে
    0.57
    噜
    0.57
    toLowerCase
    0.57
     ঘু
    0.56
    POSITIVE LOGITS
     art
    1.97
     Art
    1.80
    Art
    1.74
     artworks
    1.73
     gallery
    1.72
     Kunst
    1.72
     artists
    1.70
     galleries
    1.67
     artwork
    1.66
     Gallery
    1.66
    Activations Density 0.635%

    No Known Activations