© 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. 78781
    Prev
    Next
    INDEX
    Explanations

    credit card payments

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

    The neuron fires on phrases describing credit‐related financial terms—especially mentions of granting or reporting credit (e.g. “vendor credit,” “line of credit,” etc.).

    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
    votre
    -0.77
     Taxes
    -0.77
     kiz
    -0.75
    denn
    -0.74
    complish
    -0.73
    ֒
    -0.73
     koste
    -0.72
     歩
    -0.72
    unal
    -0.71
    xen
    -0.71
    POSITIVE LOGITS
     credit
    4.00
    credit
    2.80
     Credit
    2.80
    Credit
    2.77
     CREDIT
    2.33
     crédito
    2.30
     credits
    2.25
    CREDIT
    2.17
     кредит
    2.06
     crédit
    2.05
    Activations Density 0.023%

    No Known Activations