© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12335
    Prev
    Next
    INDEX
    Explanations

    credit scores and creditworthiness

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

    The neuron activates on mentions of credit scores or credit‐related metrics.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     returnPacket
    0.60
     무게
    0.56
     Mutter
    0.55
    fjord
    0.55
     Сере
    0.52
     bạc
    0.51
     trapezium
    0.49
     떠
    0.49
     தாய
    0.49
     Киев
    0.48
    POSITIVE LOGITS
     credit
    1.67
    credit
    1.54
     Credit
    1.48
    Credit
    1.45
     креди
    1.38
     CREDIT
    1.38
     क्रेडिट
    1.34
    信用
    1.28
     ক্রেডিট
    1.28
     crédito
    1.26
    Activations Density 0.282%

    No Known Activations