© 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. 15620
    Prev
    Next
    INDEX
    Explanations

    The neuron detects personal biographical details describing someone’s family life, hobbies, and everyday leisure activities.

    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
    こういう
    0.63
     Lovely
    0.60
     bepaalde
    0.59
    従来
    0.58
    Lovely
    0.57
    感慨
    0.57
     শোক
    0.56
    칙
    0.56
     commemoration
    0.56
     چنین
    0.55
    POSITIVE LOGITS
     catamaran
    0.78
     snorkeling
    0.72
     CrossFit
    0.70
     scuba
    0.66
     golfers
    0.65
     canoeing
    0.65
     backpacking
    0.63
     dachshund
    0.63
     steelhead
    0.63
     ukulele
    0.61
    Activations Density 0.223%

    No Known Activations