© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 61485
    Prev
    Next
    INDEX
    Explanations

    code files and foreign words

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

    The neuron strongly activates on numeric literals and version/line numbers in code (e.g. numeric tokens like “153”, “26.375”, “18.875”, debug timestamps, pragma counts, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     it
    -2.63
     you
    -1.85
     up
    -1.63
    dä
    -1.60
     einzige
    -1.59
    不斷
    -1.58
     this
    -1.50
     undergo
    -1.47
    并在
    -1.47
    It
    -1.42
    POSITIVE LOGITS
     összefoglaló
    1.68
     beiden
    1.60
    >|</
    1.56
     összefoglal
    1.52
    čení
    1.49
     klokken
    1.46
    BorderLayout
    1.46
    iações
    1.45
     kanskje
    1.45
    phère
    1.44
    Activations Density 0.054%

    No Known Activations