© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9058
    Prev
    Next
    INDEX
    Explanations

    Thailand, Baht, 於

    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
     lider
    1.13
     é
    1.12
     Unter
    1.05
     Vous
    1.03
     Cette
    1.02
     cette
    1.02
     Nous
    1.02
     Wieder
    1.02
     Ü
    1.01
     en
    1.00
    POSITIVE LOGITS
    จ
    1.71
    ภาพ
    1.63
    จะ
    1.59
    ไป
    1.58
    ห
    1.58
    มี
    1.54
    ช
    1.54
    ให้
    1.52
    พ
    1.52
    สอง
    1.52
    Activations Density 0.012%

    No Known Activations