© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38359
    Prev
    Next
    INDEX
    Explanations

    names often followed by a surname

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

    The neuron reliably activates on personal proper names, especially first names of people.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ,
    -2.19
    <tr>
    -1.92
    _{
    -1.78
    oluble
    -1.77
    <td>
    -1.70
    但是在
    -1.68
    趼
    -1.64
    From
    -1.63
    )
    -1.62
    <h2>
    -1.61
    POSITIVE LOGITS
     anderen
    2.08
     generell
    1.86
    
    1.82
     comunica
    1.76
     outros
    1.75
     verifica
    1.72
     și
    1.72
     货
    1.70
     preventiva
    1.70
     internacionais
    1.67
    Activations Density 0.053%

    No Known Activations