© 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. 90028
    Prev
    Next
    INDEX
    Explanations

    Hernandez, Hermann, Herman names

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

    The neuron fires on occurrences of the surname “Hernandez” (including its component substring “Hern”) in text.

    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
     客
    -0.83
    Lebih
    -0.77
    同志
    -0.75
    peed
    -0.74
    details
    -0.74
    zyst
    -0.73
    Betyg
    -0.73
    क्या
    -0.72
    Initializer
    -0.71
     Permian
    -0.71
    POSITIVE LOGITS
    毅
    0.80
     ethically
    0.80
    Symbolic
    0.73
    itele
    0.71
    EditForm
    0.70
    agad
    0.70
    LIT
    0.70
    لة
    0.70
     Soy
    0.69
    狠狠
    0.69
    Activations Density 0.028%

    No Known Activations