© 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. 11334
    Prev
    Next
    INDEX
    Explanations

    Bryan Stevenson, helmet, backpropagation

    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
    ing
    2.16
    y
    1.95
     It
    1.87
    c
    1.82
     This
    1.79
    yne
    1.78
    yth
    1.77
    in
    1.75
    is
    1.74
     ​​
    1.72
    POSITIVE LOGITS
     Elytres
    2.45
    柒章
    2.43
    stylers
    2.38
    三天
    2.34
    魉
    2.32
     yattha
    2.27
    ೋಜನ
    2.26
     vijj
    2.26
    陆章
    2.25
    XSSFSheet
    2.22
    Activations Density 0.031%

    No Known Activations