© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7926
    Prev
    Next
    INDEX
    Explanations

    rope, cord, cable

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

    The neuron selectively responds to numeric tokens—especially measurements, dimensions, and decimal values.

    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
    嗽
    0.68
    殼
    0.67
     muebles
    0.58
     porcel
    0.58
    窯
    0.58
    mug
    0.57
    盅
    0.56
     mugs
    0.55
    コスメ
    0.54
     gabinete
    0.54
    POSITIVE LOGITS
     rope
    1.97
     Rope
    1.88
     ropes
    1.86
    绳
    1.77
     रस्सी
    1.73
    繩
    1.66
    rope
    1.55
     twine
    1.55
     dây
    1.41
     knotted
    1.41
    Activations Density 1.020%

    No Known Activations