© 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. 10421
    Prev
    Next
    INDEX
    Explanations

    women and groups

    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
     ș
    0.98
     four
    0.96
    J
    0.90
    Z
    0.89
     трёх
    0.88
     কয়েক
    0.86
     flere
    0.86
     zwei
    0.85
     six
    0.84
     пять
    0.84
    POSITIVE LOGITS
     Whilst
    1.38
    ড়যন্ত্র
    1.31
    Whilst
    1.27
     ইউনিয়নে
    1.25
    <unused1194>
    1.24
     Watercolour
    1.24
    <unused2163>
    1.20
    <unused1251>
    1.19
     endExpNow
    1.19
    <unused1828>
    1.19
    Activations Density 0.002%

    No Known Activations