© 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. 34-GEMMASCOPE-RES-131K
    7. 32049
    Prev
    Next
    INDEX
    Explanations

    programming languages and related concepts

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

    The neuron strongly activates on mentions of programming language names.

    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
     ushort
    -0.87
    svn
    -0.86
    eclipse
    -0.83
    wikia
    -0.82
    jira
    -0.81
    edx
    -0.81
    vbo
    -0.80
     Jira
    -0.76
    ISY
    -0.75
     jira
    -0.75
    POSITIVE LOGITS
     Rust
    1.51
    Rust
    1.30
     rust
    1.23
     Actor
    0.93
     actor
    0.89
     wasm
    0.87
     rusty
    0.87
    🦀
    0.86
    rust
    0.86
     Idris
    0.84
    Activations Density 0.310%

    No Known Activations