© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109081
    Prev
    Next
    INDEX
    Explanations

    eating, hungry, food

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    お肉
    -1.63
    美味し
    -1.18
    トッピング
    -1.16
    美味しそう
    -1.16
    唐揚げ
    -1.13
    日本酒
    -1.10
     пиво
    -1.07
    ごちそう
    -1.06
     whisky
    -1.05
    玉ねぎ
    -1.05
    POSITIVE LOGITS
     food
    2.98
     eating
    2.91
     hunger
    2.58
     eat
    2.44
     hungry
    2.38
    Eating
    2.22
     Eating
    2.16
     starvation
    2.13
    eating
    2.09
     meal
    2.08
    Activations Density 0.092%

    No Known Activations