© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11578
    Prev
    Next
    INDEX
    Explanations

    Artificial Intelligence

    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
    ddots
    2.70
    ʖ
    2.51
    oka
    2.43
    ্নার
    2.41
    elti
    2.34
    udier
    2.29
    را
    2.28
    ంగ్
    2.28
     tash
    2.27
    راً
    2.21
    POSITIVE LOGITS
    ০
    2.84
    tif
    2.76
    ו
    2.67
    ์
    2.65
    潢
    2.61
    သိ
    2.56
    一个新的
    2.55
    o
    2.54
    }>
    2.51
    ી
    2.48
    Activations Density 0.023%

    No Known Activations