© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38498
    Prev
    Next
    INDEX
    Explanations

    percentage discounts and cash amounts

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

    The main thing this neuron does is find standalone numeric tokens (digits, percentages, and currency‐related amounts).

    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
     other
    -1.36
     it
    -1.29
     CascadeType
    -1.16
    jskiej
    -1.16
     necesar
    -1.13
     had
    -1.11
     where
    -1.09
     requiring
    -1.08
     this
    -1.07
     that
    -1.05
    POSITIVE LOGITS
     nejlepší
    1.21
    ṃ
    1.19
     לך
    1.19
     ſever
    1.18
     اضاف
    1.15
    Either
    1.15
    gettyimages
    1.15
    蜮
    1.14
    Countries
    1.13
     erheb
    1.13
    Activations Density 0.023%

    No Known Activations