© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 68677
    Prev
    Next
    INDEX
    Explanations

    working with others

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

    The neuron strongly responds to occurrences of the gerund “working” (as in “working with,” “working on,” “working closely,” etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    емость
    -1.59
     should
    -1.50
    洐
    -1.42
     or
    -1.41
    当然
    -1.40
     mengangg
    -1.39
    byshire
    -1.38
     of
    -1.37
    TextWatcher
    -1.37
     Abingdon
    -1.36
    POSITIVE LOGITS
     other
    1.91
     different
    1.69
    SOME
    1.60
    vermectin
    1.59
     disparate
    1.56
    €™
    1.54
    絶妙
    1.50
     некоторые
    1.49
    〬
    1.48
    mbal
    1.47
    Activations Density 0.031%

    No Known Activations