© 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. 55977
    Prev
    Next
    INDEX
    Explanations

    pancakes and crepes

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

    The neuron is tuned to detect mentions of pancakes and pancake‐related recipe terms.

    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
     candy
    -0.85
     popsic
    -0.74
     piano
    -0.72
     Terraria
    -0.70
    ahr
    -0.69
     roast
    -0.69
     Fink
    -0.69
     iv
    -0.67
    Roast
    -0.66
     procurement
    -0.65
    POSITIVE LOGITS
     pancake
    2.70
     pancakes
    2.63
    🥞
    2.38
     Pancake
    2.33
     Pancakes
    2.08
    Pancake
    1.98
     batter
    1.63
     crepe
    1.45
     crê
    1.37
     crepes
    1.37
    Activations Density 0.018%

    No Known Activations