© 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. 71392
    Prev
    Next
    INDEX
    Explanations

    legal opinions and questions

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

    This neuron identifies tokens in court‐opinion header metadata, such as opinion attributions (“Per curiam,” judge initials, “dissent,” etc.).

    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
    ﻷ
    -1.20
    abbix
    -1.05
    вольно
    -1.00
    TestTools
    -0.96
    签约
    -0.95
    بیش
    -0.93
     соответству
    -0.93
    やさ
    -0.91
    titue
    -0.91
     pleasantly
    -0.90
    POSITIVE LOGITS
     лекарства
    1.18
    ditionally
    1.16
    ditional
    1.15
    dition
    1.15
    baca
    1.07
    schaft
    1.05
     beż
    1.05
    bale
    1.05
    ǣ
    1.04
    neous
    1.03
    Activations Density 0.023%

    No Known Activations