© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 110939
    Prev
    Next
    INDEX
    Explanations

    Object-Oriented Programming (OOP)

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

    references to object-oriented programming concepts and terminology.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The main thing this neuron does is detect mentions of object-oriented programming (e.g. “object oriented,” “OOP,” related abbreviations).

    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
     when
    -1.61
     cuando
    -1.44
     когда
    -1.43
     by
    -1.42
     to
    -1.37
     any
    -1.34
     on
    -1.33
    ectomy
    -1.33
     όταν
    -1.31
     children
    -1.30
    POSITIVE LOGITS
    殽
    1.44
     ușor
    1.41
     plastiques
    1.38
    années
    1.38
     柄
    1.37
     alça
    1.36
     aéri
    1.35
     ſtill
    1.34
     aéro
    1.32
     éner
    1.31
    Activations Density 0.031%

    No Known Activations