© 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. 12447
    Prev
    Next
    INDEX
    Explanations

    understand / understanding

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

    The neuron fires on words and phrases expressing empathy, emotional awareness, or compassionate understanding.

    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
    দানি
    0.58
    取引
    0.56
    ⌜
    0.55
     deems
    0.54
     Indic
    0.54
     deemed
    0.52
     ornamental
    0.52
     INDIC
    0.52
     jewel
    0.51
    掸
    0.50
    POSITIVE LOGITS
    Understand
    2.08
    understand
    2.02
     understand
    1.98
     Understand
    1.98
     empath
    1.84
     sympathize
    1.82
     understands
    1.80
     begrij
    1.80
    理解
    1.79
     sympath
    1.76
    Activations Density 0.302%

    No Known Activations