© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 92499
    Prev
    Next
    INDEX
    Explanations

    Dancing partners and contestants

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

    The neuron strongly activates on multi‐token proper names and titles—especially celebrity names and TV show titles (e.g. “Val Chmerkovskiy,” “Dancing with the Stars”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     приобре
    -0.71
    殿下
    -0.68
    ardin
    -0.67
     Schmitz
    -0.66
     internas
    -0.65
     halen
    -0.64
     omt
    -0.63
    顏色
    -0.63
    opposed
    -0.63
     classic
    -0.62
    POSITIVE LOGITS
    Dancing
    1.41
     Dancing
    1.35
    DW
    1.31
     DW
    1.29
     ballroom
    1.19
    Derek
    0.96
     Ballroom
    0.95
     Peta
    0.90
     danced
    0.88
     Mirror
    0.87
    Activations Density 0.021%

    No Known Activations