© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54109
    Prev
    Next
    INDEX
    Explanations

    financial amounts and units

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

    The neuron activates on numeric data tokens—digits, percentages, monetary amounts, and other statistical 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_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
     گیاه
    -1.17
     растения
    -1.16
    基于
    -1.13
    〔
    -1.10
     to
    -1.08
     оригі
    -1.07
    When
    -1.07
     ragazzo
    -1.06
    ufnahme
    -1.03
    无论
    -1.02
    POSITIVE LOGITS
    ּוֹ
    1.38
     впервые
    1.09
    戌
    1.08
    bibliography
    1.07
     yves
    1.05
    CHRE
    1.05
    的气息
    1.05
    chauer
    1.04
    がたくさん
    1.03
    ִּ
    1.02
    Activations Density 0.011%

    No Known Activations