© 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. 66312
    Prev
    Next
    INDEX
    Explanations

    roles and statuses

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

    The neuron detects formal legal citations and statutory references (e.g. case names, section symbols, dates, docket numbers).

    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
    ̗
    -0.97
     within
    -0.89
     approximately
    -0.87
     twelve
    -0.86
    ̼
    -0.85
     typically
    -0.81
     today
    -0.81
     roughly
    -0.79
     demonstrating
    -0.78
     vieja
    -0.77
    POSITIVE LOGITS
    nessed
    0.84
     "..\..\
    0.82
    гова
    0.81
     mao
    0.81
    Idea
    0.80
    вец
    0.80
    ittä
    0.79
    倔
    0.78
    けている
    0.77
    expressed
    0.77
    Activations Density 0.003%

    No Known Activations