© 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. 2863
    Prev
    Next
    INDEX
    Explanations

    cooking process

    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
     crumbled
    0.82
     buttermilk
    0.80
    termilk
    0.76
     remix
    0.73
    摻
    0.73
     trộn
    0.72
     Emiliano
    0.70
    掺
    0.70
     تز
    0.69
     mixes
    0.68
    POSITIVE LOGITS
     cooking
    1.93
     cook
    1.92
    cook
    1.85
     Cook
    1.79
    Cook
    1.77
    cooking
    1.75
     Cooking
    1.70
    Cooking
    1.65
     cooker
    1.61
     cooks
    1.60
    Activations Density 0.239%

    No Known Activations