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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10387
    Prev
    Next
    INDEX
    Explanations

    technical drawings and plans

    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
     Festivals
    0.97
     pandemics
    0.95
    festival
    0.91
     Festival
    0.90
     Pentecost
    0.89
     infect
    0.87
    Festival
    0.86
    璨
    0.85
     festivals
    0.85
     festival
    0.84
    POSITIVE LOGITS
     drawings
    2.75
     drawing
    2.73
     Drawings
    2.62
     DRAW
    2.55
    draw
    2.53
     Drawing
    2.51
     draw
    2.44
    Draw
    2.42
    Drawing
    2.37
     drawn
    2.35
    Activations Density 0.445%

    No Known Activations