© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 115548
    Prev
    Next
    INDEX
    Explanations

    money and payments

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

    The neuron fires on numeric tokens—especially multi‐digit figures like counts, monetary amounts, percentages, and other quantities.

    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
    姈
    -0.95
     ideale
    -0.95
    ऑ
    -0.93
    絝
    -0.86
     filós
    -0.83
    Ещё
    -0.83
     volantes
    -0.82
     verticale
    -0.82
     lente
    -0.82
    और
    -0.81
    POSITIVE LOGITS
     £
    1.23
     circa
    1.08
     rises
    0.91
     eradicated
    0.89
     claw
    0.89
     uplift
    0.87
    abril
    0.86
    筵
    0.84
    CIF
    0.83
    -£
    0.82
    Activations Density 0.049%

    No Known Activations