© 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. 7132
    Prev
    Next
    INDEX
    Explanations

    academic citations

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

    The neuron is detecting the pipe character “|” used as a delimiter in code or tabular data.

    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
     instead
    -1.02
     that
    -0.96
    视着
    -0.94
     млрд
    -0.87
     arXiv
    -0.85
    missible
    -0.85
     because
    -0.85
     частности
    -0.85
    versen
    -0.84
    ご了承
    -0.84
    POSITIVE LOGITS
    0
    1.38
    nological
    1.07
    ляем
    1.00
     ۰
    0.97
    ０
    0.95
     первого
    0.95
    positivos
    0.94
    gehende
    0.94
    IVID
    0.93
    ༠
    0.92
    Activations Density 0.060%

    No Known Activations