© 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. 97915
    Prev
    Next
    INDEX
    Explanations

    female given names followed by surnames

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

    The neuron responds to personal names (proper nouns referring to people).

    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
    Either
    -0.92
     السيد
    -0.89
    ulatum
    -0.88
     ジャパン
    -0.87
     Either
    -0.85
     either
    -0.80
    either
    -0.79
    Gemeinden
    -0.77
     作り方
    -0.77
     نہیں
    -0.76
    POSITIVE LOGITS
    Poor
    0.76
     ImportError
    0.74
    勝負
    0.71
     he
    0.69
    Matching
    0.69
    \}.
    0.69
     حجم
    0.68
    hoid
    0.68
     personeel
    0.68
    Παραπομπές
    0.67
    Activations Density 0.043%

    No Known Activations