© 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. 10-GEMMASCOPE-RES-131K
    7. 20932
    Prev
    Next
    INDEX
    Explanations

    common usage of work

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

    This neuron activates on the root “work” (e.g. work, works, pattern work, analytical work, community leadership work, development work).

    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
     only
    -1.79
    .
    -1.75
    骘
    -1.44
     five
    -1.41
     merely
    -1.41
     four
    -1.35
    猡
    -1.34
     three
    -1.34
     wich
    -1.31
     widely
    -1.29
    POSITIVE LOGITS
    </strong>
    2.38
     halben
    1.62
    縢
    1.56
     schafft
    1.52
     täglichen
    1.49
    今度
    1.48
    の新
    1.47
    縠
    1.45
    itorious
    1.43
     PUSTAKA
    1.43
    Activations Density 0.022%

    No Known Activations