© 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. 14166
    Prev
    Next
    INDEX
    Explanations

    logical connectives

    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
     পেরিয়ে
    0.61
     $=$
    0.61
    してから
    0.61
    吩
    0.55
     $+$
    0.55
     సన్నివేశ
    0.55
     rejoint
    0.54
    到现在
    0.54
    Mental
    0.54
    IUM
    0.53
    POSITIVE LOGITS
    且
    1.40
     ∀
    1.28
    ∀
    1.10
     wobei
    1.05
     причем
    1.00
     其中
    0.97
    かつ
    0.93
    并且
    0.91
     dimana
    0.91
    ;|
    0.90
    Activations Density 0.008%

    No Known Activations