© 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. 34-GEMMASCOPE-RES-131K
    7. 118367
    Prev
    Next
    INDEX
    Explanations

    legal and financial terms

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

    This neuron fires on formal legal descriptions of U.S. and American entities—especially mentions of “U.S. citizens,” “American forces,” and related nationality terms in court‐case contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     they
    -0.94
     다시
    -0.91
     灰色
    -0.84
    gewiesen
    -0.80
     you
    -0.79
     beziehungs
    -0.79
     红色
    -0.79
    cepto
    -0.79
     cirka
    -0.78
    徇
    -0.78
    POSITIVE LOGITS
     "`
    1.32
    想要
    1.01
     merely
    1.00
     "'
    0.95
    В
    0.94
     purely
    0.92
    atisfied
    0.91
    อยาก
    0.89
    介绍
    0.86
    自分の
    0.86
    Activations Density 0.045%

    No Known Activations