© 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. 35347
    Prev
    Next
    INDEX
    Explanations

    code delimiters and assignments

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

    The neuron activates on occurrences of the “+=” operator (augmented assignments/event‐handler hookups).

    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
     createSlice
    -1.11
    そして
    -1.05
     Tipp
    -1.01
    lijken
    -0.99
    łej
    -0.96
    vertising
    -0.96
    кипедия
    -0.91
     sicherzustellen
    -0.91
    akyti
    -0.90
     powiedział
    -0.90
    POSITIVE LOGITS
    大体
    1.10
     of
    1.01
     будет
    1.00
     such
    0.98
    はお
    0.96
     labai
    0.93
    excellents
    0.93
     tantas
    0.92
     заявление
    0.91
    ambo
    0.90
    Activations Density 0.000%

    No Known Activations