© 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. 67686
    Prev
    Next
    INDEX
    Explanations

    defining a function

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

    This neuron detects function-definition signatures (i.e. the “function …” lines) in code.

    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
     parfüm
    -2.44
     parfü
    -2.03
     แต่
    -1.98
     potrebné
    -1.91
     continúas
    -1.91
    鼷
    -1.88
     beslu
    -1.80
     abiye
    -1.80
     anadolu
    -1.78
     merak
    -1.77
    POSITIVE LOGITS
     is
    1.99
    Does
    1.80
    Also
    1.70
    This
    1.68
    Maybe
    1.67
    ïdes
    1.66
    for
    1.66
    Should
    1.58
    Perhaps
    1.55
    What
    1.53
    Activations Density 0.004%

    No Known Activations