© 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. 13847
    Prev
    Next
    INDEX
    Explanations

    expertise

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

    The neuron fires on occurrences of the noun “expertise.”

    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
    »,
    -2.56
     in
    -2.56
     «
    -2.55
    蕷
    -2.50
    ꜆
    -2.50
    %).
    -2.47
    </i>
    -2.47
     {
    -2.39
     progressing
    -2.27
    mpagne
    -2.23
    POSITIVE LOGITS
    ྅
    2.94
    Adverten
    2.70
     leaſt
    2.69
    
    2.69
     thee
    2.66
     doen
    2.63
    wasn
    2.59
    became
    2.48
    ﮟ
    2.47
     hadde
    2.45
    Activations Density 0.002%

    No Known Activations