© 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. 37909
    Prev
    Next
    INDEX
    Explanations

    bankruptcy proceedings

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

    This neuron detects mentions of “Bankruptcy” (including its subword parts) and related bankruptcy-court references.

    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
    demie
    -0.74
    esperienza
    -0.71
    response
    -0.71
     rainfall
    -0.70
    POK
    -0.70
    COA
    -0.69
     Sigmund
    -0.68
     largura
    -0.68
     Dres
    -0.68
    BIOL
    -0.68
    POSITIVE LOGITS
    rupt
    1.45
    rupted
    1.33
    rupts
    1.30
    cies
    1.09
     rupt
    1.03
    upt
    1.02
    RUP
    0.94
    rup
    0.87
     trustee
    0.87
    ruptcy
    0.87
    Activations Density 0.059%

    No Known Activations