© 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-16K
    7. 3268
    Prev
    Next
    INDEX
    Explanations

    regular expression, use case, square root

    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_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
    -,
    0.87
    ၊
    0.79
     ಹಾಗೂ
    0.73
     、,
    0.72
    älfte
    0.71
    และ
    0.71
     ಮತ್ತು
    0.71
    又は
    0.70
     ຫຼື
    0.70
    몇
    0.69
    POSITIVE LOGITS
     boilerplate
    0.66
     prêts
    0.65
    صحاب
    0.63
    の外
    0.62
    CameraController
    0.62
     ec
    0.62
     ovo
    0.62
    voxel
    0.60
     écoles
    0.60
     sci
    0.60
    Activations Density 0.443%

    No Known Activations