© 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. 11810
    Prev
    Next
    INDEX
    Explanations

    Rust code includes `use` [`fn` or `struct`]

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

    Rust programming language code, particularly focusing on syntax elements like underscores, type declarations, and module paths.

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

    This neuron detects fragments of Rust source code, especially the token “rust” and related markers like “.rs” and Cargo metadata.

    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
    鳢
    -1.52
    bė
    -1.45
    itação
    -1.38
     років
    -1.37
    paramString
    -1.37
    ᱓
    -1.36
    ᠂
    -1.34
     fentanyl
    -1.31
    ilangkan
    -1.30
    ⫘
    -1.30
    POSITIVE LOGITS
     
    1.50
    叼
    1.37
    一言
    1.34
    舐
    1.25
     was
    1.21
    繊細
    1.20
    \
    1.20
     so
    1.20
    ↵↵↵
    1.20
     none
    1.19
    Activations Density 0.054%

    No Known Activations