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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 7698
    Prev
    Next
    INDEX
    Explanations

    sugar or sugars

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

    sugar and its contexts

    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_53_width_65k_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
    Titanic
    0.47
     Titanic
    0.46
     Volvo
    0.42
    Seattle
    0.42
     ভূপ
    0.42
    Volvo
    0.41
     Seattle
    0.40
    牡
    0.40
     Linux
    0.39
     hd
    0.39
    POSITIVE LOGITS
     sugar
    4.59
    sugar
    4.31
     Sugar
    4.28
    Sugar
    4.22
    糖
    3.92
     sugars
    3.91
     сахар
    3.55
     açúcar
    3.42
     azúcar
    3.41
    砂糖
    3.36
    Activations Density 0.160%

    No Known Activations