© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 3614
    Prev
    Next
    INDEX
    Explanations

    Hugh followed by a surname

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

    The neuron activates on occurrences of the given name “Hugh.”

    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
    ↵↵
    -3.55
     a
    -2.69
     speziellen
    -2.67
     vollständ
    -2.55
    瑧
    -2.47
     wichtigen
    -2.38
     Erfol
    -2.33
     zusätzlichen
    -2.30
    媗
    -2.27
     We
    -2.25
    POSITIVE LOGITS
    s
    5.03
     provoque
    2.77
    said
    2.66
    9
    2.45
     hemd
    2.42
    dámské
    2.34
     westfalen
    2.31
     eût
    2.30
    r
    2.30
    genommen
    2.28
    Activations Density 0.002%

    No Known Activations