© 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. 34-GEMMASCOPE-RES-131K
    4. 118222
    Prev
    Next
    INDEX
    Explanations

    parallel processing and computing

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

    The neuron fires on any occurrence of the substring “parallel” (in any case or as part of a larger word, e.g. “Parallel,” “parallel,” “parallelize”).

    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
     замок
    -0.73
    Kus
    -0.71
     править
    -0.70
     PCM
    -0.69
    iped
    -0.69
     Lw
    -0.69
    ugas
    -0.68
    帧
    -0.66
    urata
    -0.66
     bluff
    -0.66
    POSITIVE LOGITS
    InSeconds
    0.81
     fractions
    0.80
    ism
    0.79
    ネット
    0.78
    矯
    0.74
     sellers
    0.73
    token
    0.72
     tę
    0.71
     profitable
    0.71
    haa
    0.70
    Activations Density 0.050%

    No Known Activations