© 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. 50262
    Prev
    Next
    INDEX
    Explanations

    Stewart and Stuart variations

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

    The neuron fires strongly on occurrences of the proper name “Stewart.”

    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
    ErrUnexpectedEOF
    -0.86
    DeviceType
    -0.82
     větší
    -0.81
    TableField
    -0.81
     preparando
    -0.79
     celana
    -0.78
    autoComplete
    -0.78
     censo
    -0.78
     crucero
    -0.77
    rond
    -0.77
    POSITIVE LOGITS
     vea
    0.90
    </
    0.87
    енно
    0.86
    جرة
    0.85
    inek
    0.84
    кому
    0.84
    ネス
    0.84
    étal
    0.82
    ainen
    0.81
     efficace
    0.81
    Activations Density 0.005%

    No Known Activations