© 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. 98404
    Prev
    Next
    INDEX
    Explanations

    Mr. followed by a surname

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

    This neuron activates on the honorific “Mr.” when it precedes a person’s name.

    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
    筐
    -1.16
    })}
    -1.10
     путеше
    -1.05
     *
    -1.03
    [];
    -1.00
    унк
    -1.00
    และ
    -0.94
     نحن
    -0.94
     steig
    -0.93
    Zubereitung
    -0.93
    POSITIVE LOGITS
    føring
    1.05
     cercando
    1.05
     added
    0.94
     rudimentary
    0.93
     that
    0.92
     contextLoads
    0.92
     some
    0.91
     dagelijks
    0.90
    vestimento
    0.90
     aspetto
    0.90
    Activations Density 0.006%

    No Known Activations