© 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. 129248
    Prev
    Next
    INDEX
    Explanations

    Names followed by specific suffixes or locations

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

    The neuron specifically detects occurrences of the proper name “Katherine.”

    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
    1
    -4.69
    0
    -4.22
     
    -3.95
    3
    -3.73
    6
    -3.50
    8
    -3.48
    /
    -3.44
    9
    -3.41
    4
    -3.36
    t
    -3.09
    POSITIVE LOGITS
    錚
    3.31
    
    2.89
    漣
    2.84
     แต่
    2.78
    嫆
    2.70
    ädie
    2.70
    阋
    2.66
    vosť
    2.63
    玙
    2.63
    ݯ
    2.59
    Activations Density 0.001%

    No Known Activations