© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73298
    Prev
    Next
    INDEX
    Explanations

    michelle followed by surname

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

    The neuron activates on specific capitalized proper nouns—most notably the personal name “Michelle.”

    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
     presidencia
    -3.00
    </strong>
    -2.75
    ."
    -2.69
    </u>
    -2.58
     Are
    -2.48
    ௜
    -2.42
     inauguración
    -2.42
     of
    -2.39
     asamblea
    -2.38
    ,'
    -2.34
    POSITIVE LOGITS
    ка
    2.52
    驁
    2.47
     systé
    2.41
    Our
    2.39
    They
    2.38
    before
    2.36
     desnuda
    2.34
    ſelves
    2.33
    With
    2.31
    なんだか
    2.31
    Activations Density 0.005%

    No Known Activations