© 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. 22-GEMMASCOPE-RES-131K
    7. 73793
    Prev
    Next
    INDEX
    Explanations

    function definitions in code

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

    This neuron activates on the keyword “function,” i.e. spots function definitions or declarations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     desfile
    -1.64
     such
    -1.49
    ୈ
    -1.45
    urcht
    -1.42
    lampe
    -1.42
     dikirim
    -1.41
    ⍢
    -1.41
     mengirim
    -1.41
     memeriksa
    -1.41
     coronel
    -1.40
    POSITIVE LOGITS
    0
    1.88
    p
    1.86
    k
    1.70
    </em>
    1.68
    </h4>
    1.57
    </h2>
    1.54
    l
    1.52
    el
    1.52
    z
    1.51
    g
    1.48
    Activations Density 0.002%

    No Known Activations