© 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. 34842
    Prev
    Next
    INDEX
    Explanations

    US court documents and code headers

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

    The neuron detects references to U.S. Courts of Appeals, especially the circuit designation (e.g. “First Circuit”).

    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
    CCA
    -0.88
     Maine
    -0.70
    Arizona
    -0.69
    氫
    -0.68
     glycerol
    -0.67
     Massachusetts
    -0.65
     dishon
    -0.65
    ORG
    -0.65
    ota
    -0.65
    キャラ
    -0.64
    POSITIVE LOGITS
    michael
    0.65
    /**
    0.63
     pittura
    0.63
     Neste
    0.63
     Wraith
    0.62
    ரிய
    0.61
     Leopoldo
    0.61
    Novo
    0.61
    点赞
    0.61
     Toler
    0.60
    Activations Density 0.066%

    No Known Activations