© 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. 39372
    Prev
    Next
    INDEX
    Explanations

    percentage discounts or savings

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

    The neuron fires on numeric percentage values (including those with decimal points) appearing 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
     However
    -1.78
    4
    -1.77
    蒸し
    -1.75
    9
    -1.66
    8
    -1.65
    ,
    -1.64
    0
    -1.64
     Then
    -1.59
    </b>
    -1.59
     in
    -1.56
    POSITIVE LOGITS
    
    1.73
    
    1.70
    ſſen
    1.67
    ſſi
    1.61
     spesso
    1.55
    LLocation
    1.55
     například
    1.55
     sillas
    1.52
     complesso
    1.52
     özellikleri
    1.51
    Activations Density 0.011%

    No Known Activations