© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8446
    Prev
    Next
    INDEX
    Explanations

    sugar

    np_acts-logits-general · gemini-2.5-flash-lite

    sugar and its intake

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    каза
    0.46
    铨
    0.45
    unati
    0.44
    irds
    0.42
    牡
    0.42
    鲶
    0.42
    刑事
    0.42
     Interpol
    0.42
     Blazers
    0.42
    🐔
    0.41
    POSITIVE LOGITS
     sugar
    2.52
    sugar
    2.38
     Sugar
    2.36
    Sugar
    2.31
    糖
    2.22
     сахар
    2.08
    砂糖
    2.08
     sugars
    2.06
     sugary
    1.99
     şeker
    1.94
    Activations Density 0.326%

    No Known Activations