© 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. 10-GEMMASCOPE-RES-131K
    7. 118912
    Prev
    Next
    INDEX
    Explanations

    legal briefs and dissents

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

    This neuron detects references to filing an amicus (“friend‐of‐the‐court”) brief in court documents.

    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
     what
    -1.47
     wavering
    -1.45
     gewann
    -1.41
     เปิด
    -1.41
    ～。
    -1.39
    What
    -1.38
     Якщо
    -1.38
     unwit
    -1.37
     якщо
    -1.34
    quierda
    -1.34
    POSITIVE LOGITS
    s
    1.78
     pesso
    1.64
     anden
    1.59
    越來
    1.59
    \
    1.58
     certains
    1.48
    橚
    1.45
    苼
    1.44
     baden
    1.41
    .=
    1.40
    Activations Density 0.087%

    No Known Activations