© 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. 60731
    Prev
    Next
    INDEX
    Explanations

    parallel programming utilities

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

    The neuron fires on the word (or sub‐word) immediately following the token “parallel.”

    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
    🎡
    -0.87
    管理员
    -0.85
    ALLAS
    -0.84
    くなり
    -0.82
    澪
    -0.81
    Namaste
    -0.81
     cenderung
    -0.79
    BRARY
    -0.79
    equila
    -0.78
     daar
    -0.77
    POSITIVE LOGITS
    document
    0.93
     document
    0.89
     distanza
    0.85
    ticulture
    0.79
     here
    0.79
    仍然
    0.79
     training
    0.77
     Page
    0.75
    Lit
    0.75
    Page
    0.74
    Activations Density 0.002%

    No Known Activations