© 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. 66149
    Prev
    Next
    INDEX
    Explanations

    legal case titles with appellant/defendant

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

    The neuron spotlights the document’s prominent content words—especially proper nouns, key topic terms, and legal role labels (e.g. “Appellant,” “Defendant,” major subject nouns).

    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
    QUÉ
    -1.24
    Flug
    -1.13
    inigte
    -1.10
    Boxscore
    -1.09
     Zwar
    -1.06
     Intense
    -1.05
     lustrous
    -1.03
    ROBERT
    -1.01
     जी
    -1.00
     écl
    -1.00
    POSITIVE LOGITS
     when
    1.34
     they
    1.21
     its
    1.20
     which
    1.16
    They
    1.15
    they
    1.09
     called
    1.07
     последний
    1.06
    When
    1.06
     these
    1.02
    Activations Density 0.189%

    No Known Activations