© 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. 104584
    Prev
    Next
    INDEX
    Explanations

    names of people

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

    The neuron strongly activates on proper names—especially personal last names or full personal names.

    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
     that
    -1.73
     they
    -1.41
     have
    -1.41
     metodología
    -1.40
     everything
    -1.30
    ırken
    -1.23
     could
    -1.15
     sayfa
    -1.15
     ought
    -1.14
    でしたが
    -1.14
    POSITIVE LOGITS
    Также
    1.38
     также
    1.38
    Also
    1.36
     również
    1.36
    Объем
    1.32
     贝
    1.30
    roffenen
    1.30
    AutoModerator
    1.27
     także
    1.27
     различни
    1.26
    Activations Density 0.204%

    No Known Activations