© 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. 34-GEMMASCOPE-RES-131K
    4. 109155
    Prev
    Next
    INDEX
    Explanations

    programming languages

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

    This neuron detects the names of programming languages and related technology identifiers (e.g. “Swift,” “C#,” “C++,” “TypeScript,” 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_34/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
     python
    -1.08
     Spanish
    -1.02
     Python
    -0.98
     Swedish
    -0.96
     javascript
    -0.93
     FORTRAN
    -0.93
    python
    -0.91
     java
    -0.90
     Dutch
    -0.90
     JavaScript
    -0.89
    POSITIVE LOGITS
     language
    1.22
    speaking
    1.05
     языке
    1.03
    /.
    0.95
     /.
    0.93
    language
    0.93
    nelles
    0.90
     Language
    0.89
     speaking
    0.89
     vial
    0.88
    Activations Density 0.227%

    No Known Activations