© 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. 31-GEMMASCOPE-2-RES-65K
    7. 16035
    Prev
    Next
    INDEX
    Explanations

    sugar and sweeteners

    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_31_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
     cuir
    0.49
     Laplacian
    0.45
    舰
    0.44
    enciais
    0.42
     груп
    0.42
     palladium
    0.42
     ভূপ
    0.41
    ціа
    0.41
     battleship
    0.41
     samurai
    0.41
    POSITIVE LOGITS
     sugar
    1.41
    Sugar
    1.35
     Sugar
    1.34
    sugar
    1.29
    糖
    1.27
     sweetener
    1.09
     sugars
    1.05
    Glucose
    1.02
    🍭
    1.02
     sugary
    1.02
    Activations Density 0.101%

    No Known Activations