© 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. 66031
    Prev
    Next
    INDEX
    Explanations

    programming construct definitions

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

    The neuron flags object-oriented programming construct keywords—terms that declare or describe classes, methods, instances, inheritance/implementation, 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
     depender
    -1.16
     Resumen
    -1.07
    transpiration
    -1.06
    зависи
    -1.05
     producent
    -1.05
    ↵
    -1.04
     เพื่อ
    -1.03
    *
    -1.02
    ależ
    -1.02
     каждо
    -1.02
    POSITIVE LOGITS
     its
    1.39
     getting
    1.34
     being
    1.31
    krankungen
    1.27
    loroethene
    1.27
    我没
    1.26
     compró
    1.23
    殄
    1.23
    我还是
    1.22
     distintas
    1.20
    Activations Density 0.034%

    No Known Activations