© 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. 13121
    Prev
    Next
    INDEX
    Explanations

    python PIL image manipulation

    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
    ຍ
    2.88
    pl
    2.55
    HING
    2.49
    ると
    2.48
    ளாக்
    2.47
    ja
    2.44
    con
    2.38
     taxing
    2.33
    stop
    2.21
    empre
    2.18
    POSITIVE LOGITS
    a
    4.79
    ه
    4.26
    ン
    4.11
    ाने
    3.85
    e
    3.85
    ați
    3.84
    د
    3.83
    ে
    3.77
    aib
    3.68
    aat
    3.60
    Activations Density 0.017%

    No Known Activations