© 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. 22-GEMMASCOPE-2-RES-262K
    7. 5586
    Prev
    Next
    INDEX
    Explanations

    quadratic equations with x²

    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_22_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
    +)
    0.66
    Fab
    0.64
    ├──
    0.62
     पिताजी
    0.62
     Improved
    0.58
     plus
    0.58
     brother
    0.58
     Damien
    0.57
    валь
    0.57
    Brother
    0.57
    POSITIVE LOGITS
    穩
    0.77
    kmale
    0.77
     setObject
    0.76
     ક
    0.75
     শাসনের
    0.75
     medición
    0.74
     खान
    0.73
    <unused1116>
    0.73
    川
    0.73
     प्राणियों
    0.72
    Activations Density 0.001%

    No Known Activations