© 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. 9623
    Prev
    Next
    INDEX
    Explanations

    code execution and data processing

    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
    ='/
    0.87
    ('/')
    0.84
    ursos
    0.84
    ?'
    0.83
    ेशनल
    0.82
    ür
    0.79
    時には
    0.79
    ickt
    0.78
    ストン
    0.78
    丐
    0.77
    POSITIVE LOGITS
     Filler
    0.96
     bun
    0.95
     filler
    0.94
     rhombus
    0.92
    filler
    0.91
    खन
    0.89
     advent
    0.88
     refrain
    0.88
    गुना
    0.88
    Bun
    0.88
    Activations Density 0.006%

    No Known Activations