© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9888
    Prev
    Next
    INDEX
    Explanations

    dough mixing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     crackers
    0.47
     baking
    0.45
    烘
    0.44
    蛋糕
    0.43
     baked
    0.42
     rattled
    0.41
     Cakes
    0.41
     Bake
    0.40
     Betty
    0.40
     layers
    0.39
    POSITIVE LOGITS
     dough
    0.61
    dough
    0.51
     kneading
    0.48
     kne
    0.48
    团结
    0.46
     membentuk
    0.43
     Dough
    0.42
    糰
    0.42
    nton
    0.41
    团
    0.40
    Activations Density 0.068%

    No Known Activations