© 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. 119316
    Prev
    Next
    INDEX
    Explanations

    In re / of followed by names/cases

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

    The neuron detects court‐case caption phrases, especially “In the Matter of” and “In re” style headings.

    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
    奇
    -0.91
     cauſe
    -0.87
     devrait
    -0.85
     homeland
    -0.79
    ทีม
    -0.79
    αιν
    -0.78
    setGeometry
    -0.78
    觉醒
    -0.78
    França
    -0.77
     pelicula
    -0.77
    POSITIVE LOGITS
     Crimean
    0.94
     progressBar
    0.90
    each
    0.89
    //**
    0.88
    //----
    0.81
    rateur
    0.81
    ždý
    0.80
    ixote
    0.80
    mas
    0.79
    jj
    0.79
    Activations Density 0.137%

    No Known Activations