© 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. 1917
    Prev
    Next
    INDEX
    Explanations

    show you or your

    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
    navbarSupported
    2.32
    唠
    2.29
     kỳ
    2.13
    i
    2.09
    אות
    2.05
    ‌شده
    2.05
    
    2.02
     postul
    2.00
    ੱਖ
    1.99
    te
    1.96
    POSITIVE LOGITS
    ietic
    3.27
    顕
    3.17
    ว์
    3.01
     MyBatis
    2.98
    yses
    2.93
     satisfiable
    2.91
    𝐝
    2.90
     давления
    2.79
    廪
    2.79
    ubjects
    2.75
    Activations Density 0.396%

    No Known Activations