© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107353
    Prev
    Next
    INDEX
    Explanations

    carving and roasting meat

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

    The neuron strongly activates whenever the text mentions the phrase “Italian beef sandwich” (i.e. references to that specific regional food item).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    irinha
    -0.79
    Amended
    -0.75
     boite
    -0.75
     Спа
    -0.75
     Ranger
    -0.73
     Cake
    -0.73
     Conta
    -0.71
    雜
    -0.71
    著書
    -0.71
     Spike
    -0.69
    POSITIVE LOGITS
     carving
    2.78
     carve
    2.28
     carved
    2.20
     roast
    2.03
     Roast
    1.85
    carved
    1.81
    Roast
    1.75
     carvings
    1.65
     slicing
    1.52
     turkey
    1.35
    Activations Density 0.030%

    No Known Activations