© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7505
    Prev
    Next
    INDEX
    Explanations

    legal judgments overturned or struck

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

    The neuron detects legal terms that denote nullifying or reversing judicial or contractual decisions (e.g., “void,” “quash,” “overturn,” “vacated,” “remanded”).

    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
    跸
    -1.57
    usitis
    -1.49
    giarism
    -1.42
    ⩤
    -1.41
    ▭
    -1.41
    穑
    -1.41
     than
    -1.39
    oforms
    -1.38
     habló
    -1.35
     obtiene
    -1.35
    POSITIVE LOGITS
     that
    1.73
    2
    1.63
    4
    1.63
     on
    1.55
    1
    1.52
     obwohl
    1.45
     in
    1.43
     Businesses
    1.42
     by
    1.41
    즈
    1.35
    Activations Density 0.021%

    No Known Activations