© 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. 34-GEMMASCOPE-RES-131K
    7. 77741
    Prev
    Next
    INDEX
    Explanations

    cooking and grilling

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

    This neuron activates on recipe and cooking‐instruction text, flagging procedural cooking steps and related terminology.

    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
     गणना
    -0.77
     judo
    -0.77
    丞
    -0.75
     toothpaste
    -0.73
    zimmer
    -0.73
    дневно
    -0.72
    icach
    -0.71
     attentively
    -0.71
     отка
    -0.71
     رابط
    -0.70
    POSITIVE LOGITS
     grill
    2.16
     gri
    1.97
     grills
    1.51
     Gri
    1.49
     Grill
    1.45
    grill
    1.31
    gri
    1.30
    Gri
    1.30
     oven
    1.19
    Grill
    1.19
    Activations Density 0.017%

    No Known Activations