© 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. 14276
    Prev
    Next
    INDEX
    Explanations

    food and food security

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

    food security

    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
     кабе
    0.47
     谢
    0.46
    炽
    0.46
    欺
    0.45
    छि
    0.44
    平时
    0.44
    Slate
    0.42
    蒸汽
    0.42
    缎
    0.42
    唕
    0.42
    POSITIVE LOGITS
     food
    1.10
    food
    1.02
     ಆಹಾರ
    0.95
    食物
    0.93
     Food
    0.92
     FOOD
    0.92
    Food
    0.91
    FOOD
    0.89
     cibo
    0.88
     alimentaires
    0.87
    Activations Density 0.046%

    No Known Activations