© 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. 40794
    Prev
    Next
    INDEX
    Explanations

    defining functions

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

    The neuron is keyed to the JavaScript “function” keyword, strongly activating whenever it sees a function definition token.

    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
    蒾
    -2.41
     abiye
    -2.38
     komik
    -2.38
    茕
    -2.31
    
    -2.30
     dekoratif
    -2.28
    Ꮉ
    -2.27
     kalp
    -2.27
     benzin
    -2.25
     paie
    -2.23
    POSITIVE LOGITS
    The
    2.91
    0
    2.73
    So
    2.66
    k
    2.59
     However
    2.53
    (
    2.50
    =
    2.48
    <strong>
    2.41
     Because
    2.39
    </
    2.38
    Activations Density 0.008%

    No Known Activations