© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 40865
    Prev
    Next
    INDEX
    Explanations

    "Mr" followed by names

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

    This neuron detects honorific titles (e.g. “Mr,” “Ms”) used before personal names.

    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
    .
    
    -2.42
    。
    -2.23
    )=>{
    
    -2.13
    </em>
    -2.06
    </h4>
    -2.00
    __':
    
    -1.96
    '])
    
    -1.87
    >
    
    -1.87
    ++)
    
    -1.86
    ]);
    
    -1.84
    POSITIVE LOGITS
     papillon
    1.66
    グルト
    1.65
     there
    1.60
    ではでは
    1.60
     nî
    1.59
     boute
    1.59
    欵
    1.59
     jaja
    1.58
    ではまた
    1.55
    There
    1.55
    Activations Density 0.008%

    No Known Activations