© 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. 22-GEMMASCOPE-RES-131K
    7. 15374
    Prev
    Next
    INDEX
    Explanations

    code return statements

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

    The main thing this neuron does is detect the “return” keyword.

    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
    racht
    -1.00
     Italij
    -0.94
     Binnen
    -0.93
     съм
    -0.91
    åter
    -0.89
    معرفی
    -0.86
     informacija
    -0.86
    ȼ
    -0.86
    記錄
    -0.86
     为什么
    -0.85
    POSITIVE LOGITS
     nothing
    1.19
     anything
    1.07
     keinerlei
    0.96
     ekip
    0.96
     enfri
    0.94
     típico
    0.90
     rosado
    0.88
     thấm
    0.87
    まりました
    0.87
     präsentiert
    0.87
    Activations Density 0.007%

    No Known Activations