© 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. 10-GEMMASCOPE-RES-131K
    7. 128610
    Prev
    Next
    INDEX
    Explanations

    the attorney

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

    The neuron detects formal legal or government office headings, especially variants of “Office of the Attorney General.”

    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
    €“
    -1.91
    辔
    -1.80
    
    -1.79
     terão
    -1.77
     comien
    -1.76
    𓇼
    -1.75
    茕
    -1.72
    
    -1.67
    孓
    -1.66
    蹀
    -1.65
    POSITIVE LOGITS
     at
    1.95
     more
    1.85
    rovnik
    1.63
     just
    1.62
     people
    1.61
     with
    1.60
     relatively
    1.59
     pertandingan
    1.56
    just
    1.55
    閘
    1.52
    Activations Density 0.023%

    No Known Activations