© 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. 10-GEMMASCOPE-RES-131K
    4. 23931
    Prev
    Next
    INDEX
    Explanations

    quantifiers

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

    This neuron activates on numeric tokens or quantifiers—i.e. numbers (including multi-digit, decimal, or spelled-out counts) in the text.

    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
    desain
    -1.20
    FFA
    -1.20
    palla
    -1.17
    buen
    -1.16
    ACZ
    -1.14
    雷霆
    -1.11
     poitrine
    -1.09
    waist
    -1.09
    EEN
    -1.09
    CEE
    -1.08
    POSITIVE LOGITS
    没有
    1.45
     hôtel
    1.33
    不需要
    1.22
    不是
    1.20
     ersche
    1.16
     YellowPages
    1.12
    沒有
    1.11
     or
    1.11
     utilizz
    1.10
    بيرة
    1.10
    Activations Density 0.166%

    No Known Activations