© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1551
    Prev
    Next
    INDEX
    Explanations

    New Jersey

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

    The neuron detects legal citation and docket numbering (i.e. strings of numbers and court‐document identifiers).

    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
    Sanders
    -0.79
     ル
    -0.77
     top
    -0.74
    cluir
    -0.74
     transnational
    -0.72
     કે
    -0.71
     Fuller
    -0.71
     five
    -0.70
    queryset
    -0.70
     what
    -0.69
    POSITIVE LOGITS
    τρ
    0.82
     hilfiger
    0.81
     قرن
    0.81
     avon
    0.79
     رأس
    0.77
     packets
    0.75
    sept
    0.75
     loaves
    0.74
    glfw
    0.73
    demie
    0.73
    Activations Density 0.040%

    No Known Activations