© 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. 34-GEMMASCOPE-RES-131K
    7. 66407
    Prev
    Next
    INDEX
    Explanations

    criminal charges and convictions

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

    This neuron responds to criminal‐justice terminology—especially references to formal charges, pleas, felonies, convictions, and related legal proceedings.

    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
    姶
    -0.81
     Cantidad
    -0.81
     навча
    -0.80
    犠
    -0.79
    應該是
    -0.78
    麁
    -0.78
    lawayo
    -0.77
     entwickelt
    -0.76
     conhecer
    -0.76
     nenhuma
    -0.76
    POSITIVE LOGITS
     murder
    1.72
     assault
    1.65
     manslaughter
    1.54
     fraud
    1.46
     theft
    1.45
     perjury
    1.43
     burglary
    1.33
     conspiracy
    1.32
     attempted
    1.28
     kidnapping
    1.28
    Activations Density 0.110%

    No Known Activations