© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73959
    Prev
    Next
    INDEX
    Explanations

    start of proper nouns and phrases

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

    This neuron sharply activates on formal legal and judicial language—especially case citations, statutes, and other court‐opinion terminology.

    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
     οὐ
    -1.09
    珦
    -1.09
     grâce
    -1.07
     блюдо
    -1.07
    :^{
    -1.03
     maybe
    -1.02
     (“
    -1.00
     who
    -1.00
    politan
    -0.99
    を使って
    -0.97
    POSITIVE LOGITS
    比賽
    1.21
    ονται
    1.21
     обычно
    1.18
    üme
    1.18
    Converted
    1.16
    初始化
    1.13
     HttpStatusCode
    1.13
     경우
    1.13
    ēc
    1.12
     vermag
    1.12
    Activations Density 0.014%

    No Known Activations