© 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. 13-GEMMASCOPE-2-RES-16K
    7. 7309
    Prev
    Next
    INDEX
    Explanations

    main method args

    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_13_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
    тып
    1.37
    xim
    1.34
    Ⲗ
    1.31
     sinusoidal
    1.30
     illogical
    1.29
     सिग्
    1.28
     sizzling
    1.28
     allergic
    1.27
    ਖ਼
    1.27
    ѵ
    1.26
    POSITIVE LOGITS
    卫
    0.82
    部
    0.81
     Unite
    0.79
     Europe
    0.75
    身
    0.73
     general
    0.71
     America
    0.71
    i
    0.71
    衛
    0.69
     I
    0.69
    Activations Density 0.069%

    No Known Activations