© 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. 22-GEMMASCOPE-RES-131K
    7. 84500
    Prev
    Next
    INDEX
    Explanations

    court of appeals filings

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

    The neuron activates on the metadata “filed” stamps and docket‐header elements (e.g. the all-caps “FILED,” court names/circuits, dates, and other official filing labels).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     as
    -1.63
     There
    -1.46
     with
    -1.43
     all
    -1.40
    Those
    -1.35
    What
    -1.34
     Despite
    -1.34
     what
    -1.33
     What
    -1.30
     Throughout
    -1.30
    POSITIVE LOGITS
    ⏑
    1.44
    킁
    1.41
    扨
    1.41
     trám
    1.39
     навіть
    1.38
     pivotal
    1.37
     órganos
    1.34
     situés
    1.34
     trámites
    1.31
     rác
    1.30
    Activations Density 0.133%

    No Known Activations