© 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. 10-GEMMASCOPE-RES-131K
    7. 58853
    Prev
    Next
    INDEX
    Explanations

    productive use and productivity improvements

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

    The main thing this neuron does is detect mentions of “productive” or “productivity.”

    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
     impetus
    -2.08
     ſaid
    -2.03
     siitä
    -2.03
     they
    -2.02
     valentín
    -2.00
     the
    -1.91
     dieselbe
    -1.88
     crux
    -1.85
     tehdä
    -1.84
    ！」
    -1.83
    POSITIVE LOGITS
    {
    2.22
     vertes
    1.91
    .
    1.84
    n
    1.79
     белом
    1.79
     sauvage
    1.78
    ,
    1.73
    ą
    1.72
     nous
    1.71
    ஂ
    1.71
    Activations Density 0.008%

    No Known Activations