© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14603
    Prev
    Next
    INDEX
    Explanations

    Common Crawl

    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_7_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
    griffen
    2.78
    抜け
    2.36
    op
    2.32
    ఖా
    2.29
    ogs
    2.26
    ма
    2.25
    quoi
    2.24
    ⋙
    2.23
    उथ
    2.21
    جمع
    2.19
    POSITIVE LOGITS
    ्स
    2.97
    s
    2.94
    ு
    2.88
    FileVersion
    2.86
    ايا
    2.70
    ುದು
    2.70
    ი
    2.68
    ्
    2.63
     aton
    2.59
    ا۔
    2.57
    Activations Density 0.004%

    No Known Activations