© 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. 73810
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and lists

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

    The neuron strongly activates on commas (list‐ or clause‐separating punctuation).

    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
    ύν
    -0.95
     Unlike
    -0.94
    __(/*!
    -0.92
    Ｍ
    -0.91
     medical
    -0.90
     problematic
    -0.89
    úrg
    -0.86
     old
    -0.86
     back
    -0.85
     part
    -0.85
    POSITIVE LOGITS
    Сі
    0.96
     adequado
    0.84
     страницы
    0.83
    ハル
    0.83
     에서
    0.81
    orec
    0.80
     akumulator
    0.80
     recibido
    0.79
     embodi
    0.79
     hjälper
    0.79
    Activations Density 0.012%

    No Known Activations