© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9890
    Prev
    Next
    INDEX
    Explanations

    describing food dishes

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

    The main thing this neuron does is detect mentions of the word “dish” (and its close variants) referring to specific food items or recipes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    以上です
    -2.19
    昞
    -2.09
    鱘
    -1.98
     operar
    -1.96
    蒹
    -1.95
    臯
    -1.84
     chanteuse
    -1.84
    ઁ
    -1.83
     tubos
    -1.80
    趼
    -1.79
    POSITIVE LOGITS
      
    2.41
    5
    1.97
    g
    1.97
     ketika
    1.93
    那你
    1.88
    ar
    1.85
                
    1.84
    4
    1.82
    c
    1.80
    1.79
    Activations Density 0.003%

    No Known Activations