© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7751
    Prev
    Next
    INDEX
    Explanations

    dance and ballet

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

    The main thing this neuron does is find dance-related terms (words referring to dance, dancers, choreography, or dance events).

    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
     मझ
    0.59
     houseboat
    0.59
     geology
    0.56
     parasit
    0.55
     ngư
    0.55
     Gutenberg
    0.54
    벤
    0.54
     ವಾ
    0.53
     golfing
    0.53
     bloated
    0.53
    POSITIVE LOGITS
     dancers
    3.00
     dance
    2.91
     danced
    2.84
     Dance
    2.83
     dancer
    2.83
     dances
    2.77
    Dance
    2.75
     dancing
    2.72
    舞蹈
    2.72
    dance
    2.64
    Activations Density 0.507%

    No Known Activations