© 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. 22-GEMMASCOPE-RES-131K
    7. 26769
    Prev
    Next
    INDEX
    Explanations

    payment of fees, costs, or debts

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

    The neuron is tuned to words and phrases referring to monetary transactions, costs, fees, debts, and other financial amounts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    âce
    -1.00
    biendo
    -0.97
    bitkan
    -0.96
    מבר
    -0.96
    ágico
    -0.92
     Offisielt
    -0.92
    Dichloroprop
    -0.91
     emma
    -0.90
    味わ
    -0.90
     rout
    -0.88
    POSITIVE LOGITS
     for
    1.20
     acondicionado
    0.97
    you
    0.92
     egz
    0.91
     encontrar
    0.91
    zések
    0.91
     about
    0.90
     to
    0.90
    RICIA
    0.89
    ujuk
    0.89
    Activations Density 0.019%

    No Known Activations