© 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. 34-GEMMASCOPE-RES-131K
    7. 115779
    Prev
    Next
    INDEX
    Explanations

    Diana and Diane names

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

    The neuron responds to occurrences of the name stem “Dian,” i.e. tokens like Diana, Diane, Dianne, or Dianping.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     जाए
    -0.75
    ஜ
    -0.73
     incroy
    -0.73
    سرائيلي
    -0.73
    äsident
    -0.73
     incite
    -0.72
     Feinde
    -0.71
    ilistic
    -0.71
    ಕ
    -0.71
    niów
    -0.71
    POSITIVE LOGITS
    thus
    0.82
     inició
    0.81
     Lynn
    0.79
    asteel
    0.77
     Poitiers
    0.76
    Lynn
    0.75
     regard
    0.75
    Dian
    0.72
     fortsetter
    0.71
    сів
    0.71
    Activations Density 0.012%

    No Known Activations