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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12053
    Prev
    Next
    INDEX
    Explanations

    ASCII, iso, years, hours, option

    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
    ܀
    3.08
    णिज्य
    2.93
    aphor
    2.84
    Cherry
    2.75
     lám
    2.74
    𝐲
    2.73
    𝐡
    2.71
     приложение
    2.70
    ܝܢ
    2.69
    issue
    2.67
    POSITIVE LOGITS
    ه
    3.32
    a
    3.31
    تس
    3.24
    i
    3.20
    s
    3.19
    sü
    3.19
    e
    3.04
    eed
    3.01
    ing
    2.99
    ਆਂ
    2.94
    Activations Density 0.000%

    No Known Activations