© 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. 107472
    Prev
    Next
    INDEX
    Explanations

    Mathew Matthew Matt

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

    The neuron activates on occurrences of the personal name “Matt” or “Matthew” in the text.

    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
    quartile
    -0.88
    inyl
    -0.85
    Creek
    -0.85
    ragalactic
    -0.84
    ativní
    -0.83
    嵜
    -0.83
     jazz
    -0.82
    ponent
    -0.81
    tensive
    -0.79
     marital
    -0.79
    POSITIVE LOGITS
     Mat
    0.93
    resses
    0.91
    テム
    0.86
     primeira
    0.84
     cómodo
    0.82
     Matt
    0.82
     réfrigérateur
    0.81
     cantora
    0.80
     atriz
    0.78
    iltà
    0.77
    Activations Density 0.042%

    No Known Activations