© 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
    3. 53-GEMMASCOPE-2-RES-65K
    4. 17197
    Prev
    Next
    INDEX
    Explanations

    seafood and meats

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

    food items in recipes

    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
     chicken
    0.89
     shrimp
    0.87
     Chicken
    0.87
    Chicken
    0.86
     shrimps
    0.82
    鶏
    0.82
     Shrimp
    0.80
     चिकन
    0.79
    chicken
    0.77
    虾
    0.76
    POSITIVE LOGITS
     Wellington
    0.44
     done
    0.44
    done
    0.43
     رح
    0.42
    main
    0.41
    ellington
    0.41
    ington
    0.40
    tag
    0.40
    lington
    0.39
     tag
    0.39
    Activations Density 0.060%

    No Known Activations