© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22102
    Prev
    Next
    INDEX
    Explanations

    food and meals

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

    food and eating

    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_31_width_262k_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
    RESSION
    0.48
    慜
    0.46
    缡
    0.45
    职业
    0.44
    纱
    0.44
    ﺩ
    0.43
    轸
    0.43
     chromos
    0.42
    DWORD
    0.41
    躏
    0.41
    POSITIVE LOGITS
     food
    2.25
    food
    2.03
     FOOD
    1.98
     Food
    1.96
     ಆಹಾರ
    1.93
     foodie
    1.92
     comida
    1.91
     உணவு
    1.91
     الطعام
    1.90
     makanan
    1.89
    Activations Density 0.239%

    No Known Activations