© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6423
    Prev
    Next
    INDEX
    Explanations

    kitchen and oven

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

    The neuron fires on passages describing in-room kitchen amenities—particularly mentions of kitchens equipped with full-sized refrigerators/freezers and ovens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    烽
    0.52
    蓑
    0.52
     wool
    0.51
     parachute
    0.51
     ejac
    0.50
    parachute
    0.49
     Socks
    0.49
    🏉
    0.48
     socks
    0.48
     strictement
    0.47
    POSITIVE LOGITS
     kitchen
    1.73
    Kitchen
    1.72
     Kitchen
    1.70
    kitchen
    1.63
     kitchens
    1.61
     किचन
    1.48
     Küchen
    1.47
     keuken
    1.43
    キッチン
    1.41
     रसोई
    1.41
    Activations Density 0.463%

    No Known Activations