© 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. 22-GEMMASCOPE-RES-131K
    7. 130429
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on formal legal‐procedure terms—words referring to official filings, investigations, charges, warrants, or court actions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    filed complaint or warrant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     llegará
    -1.16
    $
    -1.16
     ſhould
    -1.13
     glau
    -1.09
    某种
    -1.08
     binnen
    -1.02
     oreo
    -1.00
    鬭
    -1.00
     resten
    -1.00
     mits
    -1.00
    POSITIVE LOGITS
     police
    1.73
    焄
    1.39
     about
    1.34
     aggiungere
    1.33
     complaint
    1.27
    tably
    1.27
    ַּ
    1.22
     protect
    1.21
    וּ
    1.20
     filed
    1.19
    Activations Density 0.007%

    No Known Activations