© 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. 34-GEMMASCOPE-RES-131K
    7. 99362
    Prev
    Next
    INDEX
    Explanations

    school or classmate relationships

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

    The neuron strongly activates on words that describe social relationships or interactions between characters—e.g. “friends,” “bullies,” and especially the linking “with.”

    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
    年輕
    -0.83
    Dr
    -0.83
     Dr
    -0.82
     adult
    -0.81
    年轻
    -0.80
     Mrs
    -0.77
    若い
    -0.76
     Father
    -0.75
    パパ
    -0.75
     father
    -0.73
    POSITIVE LOGITS
     classmate
    1.42
     classmates
    1.24
     girls
    1.20
    同学
    1.05
    girls
    1.04
     boys
    0.99
    女子
    0.96
    同學
    0.95
     students
    0.90
     bully
    0.90
    Activations Density 0.012%

    No Known Activations