© 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. 82411
    Prev
    Next
    INDEX
    Explanations

    ```bracket or matrix delimiters```

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

    The neuron strongly activates on left square‐bracket characters (e.g. `[` or escaped `\[`), as used in regex character‐classes or TeX/math delimiters.

    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
    していく
    -1.03
     %@",
    -0.91
    thief
    -0.83
     Auffassung
    -0.83
     will
    -0.81
     unseres
    -0.80
    (|
    -0.78
    Yar
    -0.77
    ->{
    -0.76
     its
    -0.76
    POSITIVE LOGITS
     المختلف
    1.09
    暃
    1.05
    ♜
    0.98
    같
    0.96
    出して
    0.94
    rceil
    0.94
    把你
    0.94
    POINTS
    0.93
     negativos
    0.91
    öld
    0.89
    Activations Density 0.037%

    No Known Activations