© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72573
    Prev
    Next
    INDEX
    Explanations

    `yle`, `=~`, `<%`, `sequester`, `unprocessable`

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

    The neuron is a regex‐operator detector – it fires strongly on the “=~” match operator (and only peripheral, lower activations spill over onto other rare tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ?”
    -2.94
    If
    -2.75
    -2.23
    鬭
    -2.22
     Если
    -2.19
    м
    -2.17
    蕯
    -2.17
    )-
    -2.17
    ;//
    -2.16
     discrepancy
    -2.09
    POSITIVE LOGITS
    y
    2.58
    啬
    2.56
     aren
    2.42
     beiden
    2.36
     nuove
    2.25
    o
    2.23
    also
    2.23
    の部分
    2.22
    as
    2.17
     attract
    2.16
    Activations Density 0.034%

    No Known Activations