© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9150
    Prev
    Next
    INDEX
    Explanations

    prosecutor and attorney

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

    The neuron strongly activates on words naming legal prosecutors or prosecutorial offices (e.g. “Prosecutor,” “Attorney,” “District Attorney,” etc.).

    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
    
    -1.69
     bör
    -1.59
    Jäh
    -1.59
    Spenden
    -1.54
     språk
    -1.51
     medlems
    -1.48
    Mitar
    -1.48
     kontroll
    -1.47
     tekno
    -1.47
     bygge
    -1.46
    POSITIVE LOGITS
     then
    1.88
     first
    1.48
     przód
    1.35
    0
    1.35
     serata
    1.30
     tył
    1.30
     Untersuch
    1.28
     against
    1.27
     followed
    1.26
     cerimonia
    1.22
    Activations Density 0.070%

    No Known Activations