© 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. 41-GEMMASCOPE-2-RES-262K
    7. 198386
    Prev
    Next
    INDEX
    Explanations

    sugar and candy ingredients

    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_all/layer_41_width_262k_l0_big
    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
     frigor
    0.42
     хле
    0.42
    指
    0.41
     кризи
    0.41
     UIT
    0.40
     bread
    0.40
     prejudice
    0.40
    食器
    0.39
     multilateral
    0.39
     đế
    0.39
    POSITIVE LOGITS
     candy
    1.14
     candies
    1.09
     Candy
    1.02
    Candy
    1.00
    candy
    0.99
    🍬
    0.95
     कैंडी
    0.84
    🍭
    0.73
     gummy
    0.69
     sugary
    0.63
    Activations Density 0.000%

    No Known Activations