© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66781
    Prev
    Next
    INDEX
    Explanations

    Louis followed by name

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

    The neuron strongly activates on occurrences of the proper name “Louis.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    毉
    -2.78
     gelieb
    -2.59
    耵
    -2.58
    各样的
    -2.47
    鑁
    -2.47
    tanggal
    -2.44
    谡
    -2.44
    ,”
    -2.44
     juſt
    -2.42
    waktu
    -2.39
    POSITIVE LOGITS
    ка
    3.09
    {
    2.64
     étan
    2.55
     händer
    2.48
     и
    2.33
     hır
    2.25
     We
    2.20
     aurait
    2.20
     behövs
    2.20
    this
    2.16
    Activations Density 0.015%

    No Known Activations