© 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. 130297
    Prev
    Next
    INDEX
    Explanations

    This neuron detects statement terminators in C‐style code, especially semicolons (and the “break” keyword).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    code block terminators

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     También
    -1.15
    ∆
    -1.09
     également
    -0.97
    ˃
    -0.97
     también
    -0.97
     tenerife
    -0.96
     crochê
    -0.96
     also
    -0.94
    ляли
    -0.93
     alho
    -0.93
    POSITIVE LOGITS
     all
    0.92
     had
    0.79
     vacía
    0.78
    ruptedException
    0.78
    pueden
    0.77
    煐
    0.76
     peł
    0.76
    nullptr
    0.75
    Begriffsklä
    0.75
     kendi
    0.74
    Activations Density 0.003%

    No Known Activations