© 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. 34-GEMMASCOPE-RES-131K
    7. 102754
    Prev
    Next
    INDEX
    Explanations

    work with others

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

    The neuron fires strongly on occurrences of the verb “work” (including its inflected forms like “working”).

    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
    contro
    -0.94
     متعلقه
    -0.94
    jando
    -0.93
    ="'.$
    -0.93
     imperf
    -0.93
     rasch
    -0.89
    Versus
    -0.88
     dispositifs
    -0.88
    uş
    -0.88
    engineered
    -0.85
    POSITIVE LOGITS
     with
    1.81
     on
    1.68
     in
    1.46
     closely
    1.45
     directly
    1.18
     alongside
    1.09
     within
    1.08
     across
    0.94
     Close
    0.92
     непосредственно
    0.91
    Activations Density 0.029%

    No Known Activations