© 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. 34-GEMMASCOPE-RES-131K
    7. 106614
    Prev
    Next
    INDEX
    Explanations

    legal appeals

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

    The neuron specializes in spotting formal legal or judicial procedure language (e.g. appeals, filings, court orders, parties, sentences).

    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
     sart
    -0.79
    쉘
    -0.74
     اظهار
    -0.73
    締
    -0.73
     Vertrags
    -0.72
     مساب
    -0.72
     semelhantes
    -0.72
    舩
    -0.71
    Relational
    -0.71
     iub
    -0.71
    POSITIVE LOGITS
     appeal
    4.69
     appeals
    3.83
     Appeal
    3.48
     appealed
    3.44
    Appeal
    3.34
    appeal
    3.25
     APPEAL
    2.88
     Appeals
    2.81
     appealing
    2.77
    appe
    2.67
    Activations Density 0.343%

    No Known Activations