© 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. 98210
    Prev
    Next
    INDEX
    Explanations

    Brian followed by a surname

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

    The neuron primarily detects occurrences of the name “Brian.”

    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
     shortened
    -0.91
    isuus
    -0.88
     efectivo
    -0.84
    &
    
    -0.84
    过程
    -0.84
    鬟
    -0.84
     spät
    -0.82
     gesund
    -0.82
     будут
    -0.81
     hass
    -0.81
    POSITIVE LOGITS
    ”“
    1.02
     Suomessa
    1.01
    рата
    1.00
     aforesaid
    0.98
    aleza
    0.96
     pleas
    0.94
    Thus
    0.94
    çon
    0.91
    ΡΑ
    0.89
     જે
    0.89
    Activations Density 0.007%

    No Known Activations