© 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. 22-GEMMASCOPE-RES-131K
    7. 69201
    Prev
    Next
    INDEX
    Explanations

    optional typing nullable

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

    This neuron fires on type-related tokens in code—things like type names (e.g. Dict, List, Any, string, vector), generic/type‐annotation keywords (optional, Path), and import/include of type or module definitions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     it
    -1.09
    Pozdrawiam
    -1.07
     詳細
    -0.98
    िल्म
    -0.96
    =>{
    -0.96
    pullover
    -0.94
     musique
    -0.93
     conexión
    -0.92
     tuan
    -0.92
    odeon
    -0.90
    POSITIVE LOGITS
     entweder
    1.02
    ↵
    1.02
    有时
    1.00
     either
    0.97
     siempre
    0.94
     zweier
    0.94
    either
    0.94
    有时候
    0.93
     czasem
    0.92
     иногда
    0.91
    Activations Density 0.007%

    No Known Activations