© 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. 10-GEMMASCOPE-RES-131K
    7. 85995
    Prev
    Next
    INDEX
    Explanations

    legal citations and sections

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

    The neuron activates on U.S. legal code section references (numerical statute citations).

    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
    There
    -2.36
    When
    -2.06
    For
    -1.98
    It
    -1.85
    Because
    -1.84
    Even
    -1.84
    Some
    -1.83
    If
    -1.76
    During
    -1.74
    How
    -1.72
    POSITIVE LOGITS
     dezelve
    1.79
     límites
    1.73
    倞
    1.71
     praticamente
    1.68
     verschillende
    1.66
     cauſe
    1.61
     estándares
    1.59
    崀
    1.59
    羶
    1.59
    頹
    1.57
    Activations Density 0.023%

    No Known Activations