© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 13578
    Prev
    Next
    INDEX
    Explanations

    candy and sweets

    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
    Not in Any Lists

    No Comments

    Negative Logits
    氬
    0.41
    AVLNode
    0.40
     Acoustic
    0.40
    HRIM
    0.39
    泄
    0.39
    InnoDB
    0.38
    桩
    0.38
     Engines
    0.38
     নৃ
    0.38
    缢
    0.38
    POSITIVE LOGITS
     candy
    3.41
     candies
    3.11
    candy
    2.89
     Candy
    2.83
    Candy
    2.83
     कैंडी
    2.36
    🍬
    2.33
     sweets
    2.28
     confectionery
    2.20
     chocolates
    2.08
    Activations Density 0.046%

    No Known Activations