© 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. 22-GEMMASCOPE-RES-131K
    7. 67928
    Prev
    Next
    INDEX
    Explanations

    price and currency

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

    The main thing this neuron does is detect numeric tokens (numbers, especially multi‐digit and decimal figures such as prices or measurements).

    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
     larger
    -1.23
    当我
    -1.20
     utiliza
    -1.18
     each
    -1.14
     Betrach
    -1.13
    ècie
    -1.13
     permite
    -1.10
     many
    -1.10
     christlichen
    -1.09
     activities
    -1.09
    POSITIVE LOGITS
     price
    1.39
     betrek
    1.37
     verminder
    1.31
     européennes
    1.27
     särsk
    1.26
    Transcrip
    1.26
    ztes
    1.25
    Provin
    1.23
     prices
    1.21
    Gera
    1.17
    Activations Density 0.018%

    No Known Activations