© 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. 71813
    Prev
    Next
    INDEX
    Explanations

    function return statements

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

    The neuron is detecting occurrences of return statements 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_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
    时代的
    -0.96
    Hvorfor
    -0.93
    ですので
    -0.92
    ثيل
    -0.91
     hen
    -0.89
     vermutlich
    -0.87
     Ausdrücke
    -0.87
    と思いますが
    -0.86
    幹線
    -0.86
     دارند
    -0.86
    POSITIVE LOGITS
     serão
    1.09
    ⚰
    1.02
     segítség
    1.02
    ;
    0.99
    verhältnisse
    0.96
    づけ
    0.95
    izarse
    0.94
     nieuwe
    0.94
     receta
    0.93
     betyr
    0.93
    Activations Density 0.001%

    No Known Activations