© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3566
    Prev
    Next
    INDEX
    Explanations

    directional and category terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    是一個
    0.73
     είναι
    0.72
     エネルギー
    0.68
    是一个
    0.64
    是一種
    0.63
    
    0.62
    édération
    0.62
     является
    0.61
    แตกต่าง
    0.61
     tiêu
    0.60
    POSITIVE LOGITS
    /
    0.90
     व
    0.80
     (!)
    0.78
    (!)
    0.77
     southbound
    0.75
     ও
    0.71
     &
    0.68
     wacky
    0.68
    ＆
    0.68
    (?)
    0.67
    Activations Density 0.026%

    No Known Activations