© 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. 7631
    Prev
    Next
    INDEX
    Explanations

    eating food and related actions

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

    eating and food consumption

    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
    骧
    0.40
    जेंडर
    0.39
    闱
    0.39
    楣
    0.38
    旖
    0.37
    战争
    0.37
    娌
    0.37
     लंबित
    0.37
    授权
    0.36
    谋
    0.36
    POSITIVE LOGITS
     eating
    1.05
     food
    1.02
    食べ
    1.02
     eaten
    0.99
    食物
    0.99
     foods
    0.97
    食べた
    0.97
     eat
    0.95
     alimentos
    0.93
    食べて
    0.93
    Activations Density 0.322%

    No Known Activations