© 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. 41-GEMMASCOPE-2-RES-65K
    7. 12886
    Prev
    Next
    INDEX
    Explanations

    onion

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     гульнявыя
    0.60
    舰
    0.60
     अब्दुल
    0.58
     عبدال
    0.58
    篤
    0.58
    AccessToken
    0.56
     পাখ
    0.55
    kyverno
    0.55
    Amino
    0.54
    珊瑚
    0.54
    POSITIVE LOGITS
     onion
    3.61
     Onion
    3.36
     onions
    3.28
    onion
    2.92
     प्याज
    2.80
    प्याज
    2.70
    🧅
    2.58
     garlic
    2.33
    葱
    2.31
     bawang
    2.30
    Activations Density 0.075%

    No Known Activations