© 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. 58990
    Prev
    Next
    INDEX
    Explanations

    function followed by parenthesis

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

    The neuron strongly activates on the JavaScript “function” keyword (i.e. function definitions).

    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
    preet
    -1.54
     gius
    -1.53
     späteren
    -1.44
    --
    -1.44
    -...
    -1.43
     schweren
    -1.43
     alebo
    -1.41
    nowu
    -1.41
    ations
    -1.41
    
    -1.39
    POSITIVE LOGITS
     where
    1.62
    </em>
    1.61
     by
    1.58
     to
    1.52
     —
    1.49
    、“
    1.37
     although
    1.34
     it
    1.34
     not
    1.34
     не
    1.33
    Activations Density 0.003%

    No Known Activations