© 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. 92225
    Prev
    Next
    INDEX
    Explanations

    roast chicken and meats

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

    The neuron fires strongly on numeric quantities and measurements (e.g. weights, volumes, times, counts) in cooking or instructional text.

    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
     Egg
    -0.81
    Ỗ
    -0.81
     Eggs
    -0.79
    uevas
    -0.77
    bringen
    -0.77
     egg
    -0.75
    egg
    -0.75
     Reuben
    -0.75
     edge
    -0.75
     牛肉
    -0.75
    POSITIVE LOGITS
     roast
    1.39
     whole
    1.38
     roasting
    1.30
     spit
    1.14
    whole
    1.13
     ro
    1.09
    Whole
    1.06
     Roast
    1.06
    Spit
    1.02
     roasted
    0.98
    Activations Density 0.018%

    No Known Activations