© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103110
    Prev
    Next
    INDEX
    Explanations

    crime and legal proceedings

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

    The neuron activates on legal and criminal-justice terms, especially words denoting charges, trials, convictions, sentences, and related 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_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
     этой
    -1.44
     (
    -1.35
     ڤ
    -1.34
    toda
    -1.32
    嫱
    -1.30
    tadores
    -1.29
     {
    -1.27
     vorkommen
    -1.27
     цьому
    -1.24
    -1.23
    POSITIVE LOGITS
     on
    1.46
     ‘
    1.23
     “
    1.11
     in
    1.10
     then
    1.09
    וּ
    1.06
     or
    1.06
     would
    1.02
     at
    1.02
     če
    1.01
    Activations Density 0.171%

    No Known Activations