© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57532
    Prev
    Next
    INDEX
    Explanations

    outstanding debts and bills

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

    This neuron detects mentions of financial obligations or unpaid amounts—specifically tokens of sums owed or overdue payments.

    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
    kunci
    -0.91
    información
    -0.87
    tamanho
    -0.84
    tambah
    -0.82
    sumber
    -0.77
    Acesso
    -0.76
    Apoll
    -0.76
    dijual
    -0.75
    Possui
    -0.74
    reebok
    -0.73
    POSITIVE LOGITS
     debts
    2.03
     balance
    1.74
     outstanding
    1.68
     balances
    1.58
     dues
    1.45
     debt
    1.43
    balance
    1.40
     bills
    1.36
     fines
    1.34
     fees
    1.33
    Activations Density 0.025%

    No Known Activations