© 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. 13132
    Prev
    Next
    INDEX
    Explanations

    exit

    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
    左
    0.64
     左
    0.52
    rfloor
    0.49
    ᆨ
    0.47
    鴎
    0.47
    oudre
    0.46
    ushu
    0.46
     왼
    0.46
    侔
    0.46
    SetStr
    0.45
    POSITIVE LOGITS
     exit
    5.13
     Exit
    4.88
    Exit
    4.75
    exit
    4.66
     EXIT
    4.56
     exits
    4.50
     exiting
    4.34
    EXIT
    4.28
     exited
    3.95
    退出
    3.63
    Activations Density 0.144%

    No Known Activations