© 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. 14748
    Prev
    Next
    INDEX
    Explanations

    UI events and elements

    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
    eae
    0.60
    ধার
    0.52
     ყ
    0.51
    ீர
    0.51
     бага
    0.49
    spar
    0.49
    pard
    0.49
    sting
    0.48
    e
    0.48
    ắm
    0.48
    POSITIVE LOGITS
     Gravity
    0.92
    KeyEvent
    0.91
    Gravity
    0.90
     gravity
    0.82
     Window
    0.81
    MenuItem
    0.80
     keyCode
    0.80
     Menu
    0.79
     MENU
    0.77
    Window
    0.76
    Activations Density 0.000%

    No Known Activations