© 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. 9822
    Prev
    Next
    INDEX
    Explanations

    your area

    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
     하나의
    1.05
    つ
    1.04
     تقدم
    1.01
    艨
    0.97
    অন্ত
    0.96
     aún
    0.94
    ひとつ
    0.93
    紆
    0.92
     sentences
    0.91
    разуме
    0.91
    POSITIVE LOGITS
     area
    4.44
    area
    3.91
     Area
    3.88
    Area
    3.80
     AREA
    3.79
     areas
    3.77
    areas
    3.56
     Areas
    3.45
     área
    3.36
     AREAS
    3.28
    Activations Density 0.547%

    No Known Activations