© 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. 10-GEMMASCOPE-RES-131K
    7. 19044
    Prev
    Next
    INDEX
    Explanations

    Ethan with names, analyte in samples

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

    The main thing this neuron does is detect occurrences of the name “Ethan.”

    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
    ."
    -2.53
    );
    -2.50
    逦
    -2.45
    鬭
    -2.45
     ͡°
    -2.44
    ção
    -2.42
    灕
    -2.38
    )/
    -2.36
    :";
    -2.33
    Ꮸ
    -2.33
    POSITIVE LOGITS
     I
    2.53
    izing
    2.25
    2.19
    {
    2.19
    five
    2.19
    #
    2.17
     insist
    2.17
     wou
    2.11
    so
    2.09
    い
    2.06
    Activations Density 0.003%
    No Known Activations