© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111615
    Prev
    Next
    INDEX
    Explanations

    Darren, Darryl names

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

    The neuron fires strongly on personal first names (e.g. “Darren,” “Darryl”), i.e. tokens that are people’s given 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
    蛧
    -2.70
     It
    -2.61
    塤
    -2.52
    猻
    -2.50
    戗
    -2.48
     analyze
    -2.41
    en
    -2.41
     säger
    -2.39
    a
    -2.31
     finds
    -2.25
    POSITIVE LOGITS
    跸
    2.63
    .《
    2.63
    鸶
    2.55
    ⑊
    2.52
    ᠁
    2.50
    他不
    2.45
     ſeveral
    2.41
    𐬹
    2.38
    ਗ਼
    2.36
    ––
    2.34
    Activations Density 0.006%

    No Known Activations