© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 147268
    Prev
    Next
    INDEX
    Explanations

    drive-thru window or lane

    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_29_width_262k_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
    ([^
    0.75
     ochron
    0.74
    ประก
    0.71
     धात
    0.71
     భ
    0.70
     Tyr
    0.68
    ევრი
    0.67
    ഢ
    0.67
    䣨
    0.64
     évén
    0.64
    POSITIVE LOGITS
     window
    1.03
     lane
    1.00
     Lane
    0.97
     Window
    0.92
    Lane
    0.89
    lane
    0.89
    window
    0.88
     windows
    0.84
     LANE
    0.84
     WINDOW
    0.83
    Activations Density 0.001%

    No Known Activations