© 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. 105300
    Prev
    Next
    INDEX
    Explanations

    surnames followed by vocations

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

    The neuron fires on capitalized last names of people (i.e. surnames).

    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
     его
    -1.62
    ormány
    -1.56
     they
    -1.43
     hắn
    -1.31
    枚目
    -1.27
     её
    -1.24
     viendra
    -1.23
     siè
    -1.23
    lland
    -1.20
    vestidos
    -1.20
    POSITIVE LOGITS
     also
    1.96
     to
    1.92
     that
    1.48
    ：……
    1.41
    riera
    1.40
     only
    1.32
     now
    1.26
     a
    1.20
    :`
    1.19
    邢
    1.18
    Activations Density 0.156%

    No Known Activations