© 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. 10-GEMMASCOPE-RES-131K
    7. 128788
    Prev
    Next
    INDEX
    Explanations

    spending and acquiring for specific purposes

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

    The neuron is activated by numeric expressions (especially amounts, counts, dates, or monetary figures).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     increase
    -1.20
    ที่มี
    -1.11
    el
    -1.01
     针
    -1.00
     large
    -0.99
     spiele
    -0.98
     Braut
    -0.96
     received
    -0.95
     распро
    -0.95
    ními
    -0.94
    POSITIVE LOGITS
    ītā
    1.15
    тров
    1.09
     why
    1.08
    cjonal
    1.06
    jenje
    1.06
    always
    1.06
    -------
    1.02
    嘭
    1.02
     câteva
    1.02
     pekerja
    1.01
    Activations Density 0.102%

    No Known Activations