© 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. 95475
    Prev
    Next
    INDEX
    Explanations

    argued, submitted, petition

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

    The neuron detects the formal legal‐document header elements—court names, docket numbers, dates, and other citation metadata in case headings.

    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
     data
    -1.23
     this
    -1.20
     میشه
    -1.19
     very
    -1.16
     all
    -1.15
     work
    -1.13
     خوبه
    -1.13
     biggest
    -1.11
     often
    -1.09
     many
    -1.08
    POSITIVE LOGITS
     HAVING
    1.48
    暧
    1.37
    pplung
    1.27
     inalámb
    1.26
     alberi
    1.25
     확인함
    1.23
     reemplazar
    1.23
    owi
    1.23
     Anſ
    1.22
     áng
    1.21
    Activations Density 0.284%

    No Known Activations