© 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. 34-GEMMASCOPE-RES-131K
    7. 82861
    Prev
    Next
    INDEX
    Explanations

    C/C++ data types and functions

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

    The neuron is strongly activated by left‐parenthesis tokens—i.e. occurrences of “(” typically marking function calls or 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_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
    resiasi
    -1.02
    ↵
    -0.94
    tiek
    -0.85
     electricidad
    -0.84
     eficaz
    -0.84
     boolean
    -0.84
     utilisez
    -0.84
    impre
    -0.82
     sonunda
    -0.80
     cientos
    -0.79
    POSITIVE LOGITS
    const
    1.29
     const
    0.92
     unga
    0.90
     lading
    0.88
     制
    0.87
    void
    0.85
     restric
    0.84
     Greeting
    0.84
    ونة
    0.82
    χυ
    0.80
    Activations Density 0.016%

    No Known Activations