© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103851
    Prev
    Next
    INDEX
    Explanations

    The name Marcus

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

    The neuron is primarily detecting occurrences of the personal name “Marcus.”

    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
     With
    -3.63
     If
    -3.11
    ,
    -3.09
     
    -2.75
     The
    -2.70
     Mainly
    -2.69
     You
    -2.64
     Especially
    -2.59
     Although
    -2.56
    {
    -2.56
    POSITIVE LOGITS
    螃
    3.84
    鞫
    3.36
    ਞ
    3.36
    囯
    3.05
    臜
    3.03
    archiwizowane
    2.95
    戋
    2.91
    辚
    2.89
    闼
    2.88
    阄
    2.84
    Activations Density 0.008%

    No Known Activations