© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25517
    Prev
    Next
    INDEX
    Explanations

    court decision dates

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

    This neuron activates on the word “Decided,” marking the decision-date line in a court opinion header.

    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
     \
    -1.39
     those
    -1.36
     to
    -1.28
    Those
    -1.28
    clés
    -1.18
     other
    -1.17
     folgender
    -1.16
     In
    -1.15
    0
    -1.13
    由于
    -1.12
    POSITIVE LOGITS
    奩
    1.27
    shake
    1.22
     lác
    1.21
    vielen
    1.21
     czerwca
    1.20
    ⬜
    1.20
     ชิ้น
    1.20
     października
    1.17
     świąte
    1.17
    Wady
    1.16
    Activations Density 0.000%

    No Known Activations