© 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. 15914
    Prev
    Next
    INDEX
    Explanations

    Python function definitions and code blocks

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

    The main thing this neuron does is detect the verb “play.”

    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
    鈕
    0.74
     spirited
    0.71
     dignified
    0.70
    拔
    0.70
     tireless
    0.69
     voltage
    0.66
     dignity
    0.64
    äk
    0.64
    FRINGEMENT
    0.64
    meisterschaft
    0.64
    POSITIVE LOGITS
    ência
    0.88
     vardı
    0.86
     contado
    0.84
     đã
    0.81
    で
    0.80
    да
    0.78
     कि
    0.77
    də
    0.76
     adesso
    0.76
    り
    0.75
    Activations Density 0.000%

    No Known Activations