© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31181
    Prev
    Next
    INDEX
    Explanations

    siblings and brothers

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

    The neuron is strongly activated by frequent English function words (e.g. the, of, between, with, and).

    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
    女儿
    -0.87
    老爷
    -0.82
    女兒
    -0.79
    timacy
    -0.69
     Strecken
    -0.69
    范文
    -0.68
    particle
    -0.68
     Mrs
    -0.68
    ouple
    -0.67
     Mme
    -0.66
    POSITIVE LOGITS
     brother
    5.97
     sibling
    5.06
     sister
    4.75
     brothers
    4.75
     siblings
    4.69
    brother
    4.44
    Brother
    3.91
     sisters
    3.89
     Brother
    3.83
    sibling
    3.66
    Activations Density 0.107%

    No Known Activations