© 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. 34-GEMMASCOPE-RES-131K
    7. 76667
    Prev
    Next
    INDEX
    Explanations

    bankruptcy and filings

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

    The neuron flags mentions of companies or parties in the context of bankruptcy proceedings (e.g. trustee titles, filings, and corporate names tied to bankruptcy).

    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
    チョコ
    -0.81
     erziel
    -0.79
     mutilated
    -0.77
    MathML
    -0.75
    ield
    -0.75
    PAINT
    -0.73
    ρίου
    -0.73
    бов
    -0.73
    JOH
    -0.71
    vistar
    -0.71
    POSITIVE LOGITS
     bankruptcy
    5.25
     bankrupt
    4.44
     Bankruptcy
    3.84
     insolvency
    2.89
    ruptcy
    2.20
     Insol
    2.17
     insolvent
    2.11
     Chapter
    1.82
    破
    1.74
     chapter
    1.61
    Activations Density 0.092%

    No Known Activations