© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13839
    Prev
    Next
    INDEX
    Explanations

    either

    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
     سمیت
    0.67
     સહિત
    0.64
     sempat
    0.62
    还将
    0.60
     tüm
    0.57
     அனைத்து
    0.55
    만에
    0.55
    更
    0.55
     sekaligus
    0.54
     পাশাপাশি
    0.53
    POSITIVE LOGITS
     either
    6.41
    either
    6.13
    Either
    6.00
     Either
    5.94
     entweder
    5.41
    要么
    4.69
     либо
    4.34
    ITHER
    2.97
    いずれ
    2.78
    либо
    2.63
    Activations Density 0.450%

    No Known Activations