© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130346
    Prev
    Next
    INDEX
    Explanations

    michelle followed by last name

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

    The neuron fires on capitalized personal first names—most strongly on “Michelle” (and similarly on names like “Elisabeth”).

    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
    ﮑ
    -2.86
    榀
    -2.84
    湉
    -2.83
    wertes
    -2.72
    きは
    -2.69
     แต่
    -2.64
    腘
    -2.61
    鬭
    -2.61
    贗
    -2.58
     ソックス
    -2.50
    POSITIVE LOGITS
    ed
    3.91
    8
    3.38
    en
    3.33
    на
    3.11
    5
    3.09
    a
    3.06
    1
    2.98
    7
    2.94
    3
    2.86
    os
    2.80
    Activations Density 0.010%

    No Known Activations