© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 20866
    Prev
    Next
    INDEX
    Explanations

    signed into law

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

    The neuron specializes in detecting mentions of legislation being enacted—particularly “signed into law,” references to bills or acts being signed (often by governors), and related legal enactment terms.

    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
     where
    -1.35
     our
    -1.34
    わから
    -1.27
    ?
    -1.22
     which
    -1.16
    лого
    -1.15
    𝖾
    -1.14
    son
    -1.09
    fjspx
    -1.08
     even
    -1.06
    POSITIVE LOGITS
     lengan
    1.31
    ItemClick
    1.27
    OLOGIA
    1.23
    儅
    1.22
     минуты
    1.22
     två
    1.22
    crimes
    1.22
    {|
    1.21
    Задача
    1.20
    Enllaces
    1.19
    Activations Density 0.082%

    No Known Activations