© 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. 11359
    Prev
    Next
    INDEX
    Explanations

    code explanations and error handling

    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
     套
    5.56
     也
    5.40
     啊
    5.40
     程序
    5.23
     因此
    5.18
     哦
    5.12
     沙
    5.04
     控制
    4.98
     而且
    4.92
     你
    4.88
    POSITIVE LOGITS
    tidak
    3.78
     लगाएंगे
    3.50
    baixo
    3.45
    os
    3.45
    pesar
    3.41
     muitos
    3.33
     कराएंगे
    3.27
    その
    3.24
    टेगरी
    3.20
     ampla
    3.19
    Activations Density 0.123%

    No Known Activations