© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 40930
    Prev
    Next
    INDEX
    Explanations

    brown crust or sear

    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_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Cook
    0.60
    Cook
    0.56
     COOK
    0.54
    cook
    0.52
     cook
    0.50
     Cooks
    0.47
     cooks
    0.47
    COOK
    0.47
    烹
    0.47
     nấu
    0.45
    POSITIVE LOGITS
     caramel
    1.02
     browned
    0.96
     brown
    0.93
     caramelized
    0.92
     Caramel
    0.90
    brown
    0.80
     burnt
    0.78
     коричне
    0.78
    Brown
    0.73
     burned
    0.73
    Activations Density 0.014%

    No Known Activations