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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9771
    Prev
    Next
    INDEX
    Explanations

    quantities, descriptions, and durations

    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
    ир
    0.91
    훔
    0.90
    उ
    0.89
    >©
    0.88
    淮
    0.86
    機会
    0.85
    pieces
    0.84
    ιδ
    0.84
    쇠
    0.84
     беру
    0.83
    POSITIVE LOGITS
     Pagination
    1.03
     kerja
    1.01
     Lua
    1.00
     lore
    0.99
     ਪਰ
    0.99
    মা
    0.97
     আপনাদের
    0.96
     hbox
    0.95
     computing
    0.95
     Bl
    0.94
    Activations Density 0.000%

    No Known Activations