© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116551
    Prev
    Next
    INDEX
    Explanations

    the followed by legal nouns

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

    This neuron activates on the introductory case‐description sentence in a judicial opinion (e.g. the “This is a suit brought in a state court…” summary).

    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
     upfront
    -0.99
     DOJ
    -0.94
     apareció
    -0.89
     HTC
    -0.88
    LinkedIn
    -0.86
    ourcing
    -0.85
    ClassName
    -0.82
     NYPD
    -0.82
     dage
    -0.81
    nante
    -0.81
    POSITIVE LOGITS
     instrument
    0.92
     last
    0.86
     further
    0.83
     questioned
    0.81
     challenged
    0.80
     trial
    0.79
     answering
    0.78
     criticised
    0.77
     مصر
    0.77
     cited
    0.77
    Activations Density 0.083%

    No Known Activations