© 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. 34-GEMMASCOPE-RES-131K
    4. 83124
    Prev
    Next
    INDEX
    Explanations

    Russian male names

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

    The neuron fires on capitalized name‐like tokens—especially initials and proper nouns (e.g. “S.”, “V.”, “Nikolai”, “Andrei”).

    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
    ayana
    -0.88
     Фер
    -0.84
    泾
    -0.82
    üht
    -0.79
     Constan
    -0.78
     Czar
    -0.77
    bastian
    -0.76
    věř
    -0.76
    slika
    -0.75
     présent
    -0.75
    POSITIVE LOGITS
     Fed
    1.00
     Nikon
    0.97
     Gladys
    0.96
     Sh
    0.95
    Sh
    0.93
     Sha
    0.92
     Solo
    0.90
     Yak
    0.90
     Deine
    0.87
     semen
    0.85
    Activations Density 0.040%

    No Known Activations