© 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. 22-GEMMASCOPE-RES-131K
    7. 38706
    Prev
    Next
    INDEX
    Explanations

    programming function/method definitions

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

    This neuron fires on tokens that introduce function or method definitions (e.g. def, function, public, async, void) across various programming languages.

    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
    aneity
    -1.08
    回来的
    -1.05
     any
    -1.01
    انجليز
    -0.99
     all
    -0.99
     onCancelled
    -0.98
    žně
    -0.98
     their
    -0.98
    ıkları
    -0.97
    ～。
    -0.96
    POSITIVE LOGITS
    を探す
    1.16
     automóviles
    1.10
     置物
    1.01
    쇼
    1.01
     Є
    1.00
     obé
    0.97
     trám
    0.97
     BEFORE
    0.96
     университе
    0.94
     régal
    0.94
    Activations Density 0.002%

    No Known Activations