© 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. 90764
    Prev
    Next
    INDEX
    Explanations

    Supreme Court

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

    The neuron detects mentions of Supreme Court rulings or actions in legal‐news text.

    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
    ̎
    -0.72
     γ
    -0.71
     стоимо
    -0.68
    キャスト
    -0.65
    if
    -0.65
    k
    -0.64
    CLA
    -0.64
    льга
    -0.64
    writes
    -0.63
    ()/
    -0.63
    POSITIVE LOGITS
     Supreme
    1.46
    Supreme
    1.21
     SC
    1.08
     apex
    1.00
     SUPREME
    0.96
     SCI
    0.92
     SCC
    0.91
     curative
    0.91
    SC
    0.89
    mbres
    0.84
    Activations Density 0.019%

    No Known Activations