© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 48606
    Prev
    Next
    INDEX
    Explanations

    food coloring and additives

    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_65k_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
     univariate
    0.41
    嶽
    0.41
    行驶
    0.40
    차
    0.38
    зок
    0.37
     quát
    0.37
     역사
    0.37
     پڑے
    0.37
    晞
    0.37
     ગામ
    0.36
    POSITIVE LOGITS
     coloring
    1.11
     flavoring
    1.11
    coloring
    1.02
     additives
    0.98
    色素
    0.94
     colouring
    0.93
     preservatives
    0.92
     dyes
    0.90
     Coloring
    0.90
     artificial
    0.88
    Activations Density 0.050%

    No Known Activations