© 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. 87388
    Prev
    Next
    INDEX
    Explanations

    the name Graham

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

    The neuron is primarily triggered by occurrences of the proper name “Graham.”

    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
     решения
    -2.70
    真的是
    -2.70
    的男人
    -2.61
     persino
    -2.52
    」　
    -2.48
    栳
    -2.48
    的女人
    -2.47
    ৢ
    -2.44
     glowing
    -2.42
    偌
    -2.42
    POSITIVE LOGITS
    蚡
    2.80
    弍
    2.64
    ൎ
    2.50
    g
    2.47
    geſ
    2.44
    the
    2.42
     сча
    2.34
    薆
    2.27
    .
    2.20
    </td>
    2.19
    Activations Density 0.005%

    No Known Activations