© 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. 10-GEMMASCOPE-RES-131K
    7. 48419
    Prev
    Next
    INDEX
    Explanations

    Billion, Bengali, BatchNormalization

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

    The neuron fires on occurrences of “bn” used as the abbreviation for “billion” in numerical 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_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
    咴
    -2.66
    ଞ
    -2.47
     utilizada
    -2.42
    6
    -2.41
    ୪
    -2.39
    7
    -2.38
    禤
    -2.38
    咵
    -2.34
    纔
    -2.33
    葙
    -2.31
    POSITIVE LOGITS
    enablog
    3.14
    '
    2.89
    窳
    2.39
    可以通过
    2.36
    bn
    2.28
    ни
    2.27
    爆発
    2.27
    ?"
    2.25
    section
    2.22
    纾
    2.19
    Activations Density 0.003%

    No Known Activations