© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17832
    Prev
    Next
    INDEX
    Explanations

    eat healthy food

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

    eating disorders

    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
    ylmethylsulfanyl
    0.46
    branchNode
    0.46
    壞
    0.44
    钏
    0.42
    ാ
    0.40
    myCollision
    0.40
    ποτε
    0.39
     автомо
    0.39
    ማ
    0.39
    镙
    0.39
    POSITIVE LOGITS
    drink
    0.78
     drink
    0.77
     Drink
    0.72
     eating
    0.70
    Drink
    0.68
     eat
    0.66
     Eating
    0.65
    Eating
    0.62
     makan
    0.62
    eating
    0.62
    Activations Density 0.007%

    No Known Activations