© 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. 84183
    Prev
    Next
    INDEX
    Explanations

    Alexis names

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

    The main thing this neuron does is detect occurrences of the personal name “Alexis” (and close variants like “Alexey”).

    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
     Their
    -2.84
    鬟
    -2.72
     Its
    -2.59
     kümmern
    -2.59
    IANGLES
    -2.58
    s
    -2.58
    寕
    -2.56
     However
    -2.47
     touted
    -2.42
    次的
    -2.39
    POSITIVE LOGITS
     cansado
    2.50
    珰
    2.39
     موفقیت
    2.34
     жена
    2.30
     pewno
    2.30
     exakt
    2.22
     駅前
    2.17
     измени
    2.16
    ちょこ
    2.16
     toreb
    2.14
    Activations Density 0.010%

    No Known Activations