© 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. 22-GEMMASCOPE-RES-131K
    7. 129680
    Prev
    Next
    INDEX
    Explanations

    The neuron detects mentions of monetary transactions, especially cash amounts, payments, rewards, or incentives.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    payment and rewards

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ズニー
    -1.08
    seamnă
    -1.06
     således
    -1.02
     Véri
    -0.99
     générer
    -0.98
    鐮
    -0.98
     fabriquer
    -0.97
     แฟ
    -0.97
     austerity
    -0.96
     bloquer
    -0.95
    POSITIVE LOGITS
     for
    1.43
     to
    1.38
     compensation
    1.38
     reward
    1.31
    如果
    1.17
     money
    1.14
    ให้
    1.14
     rewards
    1.09
     paid
    1.09
     compensate
    1.08
    Activations Density 0.033%

    No Known Activations