© 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. 42704
    Prev
    Next
    INDEX
    Explanations

    life of a

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

    The neuron strongly activates on the word “of” when it’s part of noun-of-noun phrases (e.g. “mind of,” “life of,” “body of”).

    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
     vorsichtig
    -1.77
     einander
    -1.67
     різних
    -1.63
     バイ
    -1.58
    って思
    -1.56
    ڧ
    -1.56
    的で
    -1.55
     フィルム
    -1.55
    㩒
    -1.50
    蹓
    -1.48
    POSITIVE LOGITS
    </h1>
    2.05
     FontWeight
    1.84
     bahwa
    1.83
     die
    1.81
     him
    1.80
     kerana
    1.63
     YOUR
    1.63
     n
    1.62
     jeho
    1.62
     ketika
    1.59
    Activations Density 0.057%

    No Known Activations