© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 14126
    Prev
    Next
    INDEX
    Explanations

    menu and navigation actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PCR
    1.02
     mPreview
    0.95
     ذریعہ
    0.89
    Мушко
    0.88
     physiological
    0.87
    fillStyle
    0.87
    ensitivity
    0.87
    얗
    0.87
     chromosomal
    0.86
     Ghulam
    0.86
    POSITIVE LOGITS
     menu
    1.43
    菜单
    1.31
     Menu
    1.30
     MENU
    1.29
    Menu
    1.26
    menus
    1.22
     menú
    1.21
     menus
    1.21
    menu
    1.15
    メニュー
    1.13
    Activations Density 0.128%

    No Known Activations