© 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. 66190
    Prev
    Next
    INDEX
    Explanations

    verbs indicating discovery or knowledge

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

    The neuron detects numeric values and quantitative measurements (e.g. integers, decimals, percentages) 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
     ApiResponse
    -1.11
    linalg
    -1.08
     スイーツ
    -1.06
    ]$}
    -1.05
     треть
    -1.05
    TRIBUN
    -1.04
     (
    -1.02
     puerta
    -1.02
    {
    -1.00
     July
    -1.00
    POSITIVE LOGITS
     peuvent
    1.17
     ندارم
    1.13
    cepatan
    1.07
    짙
    1.07
    ICHE
    1.05
    acherous
    1.05
    
    1.04
    ERNES
    1.03
    erobic
    1.02
     offerte
    1.02
    Activations Density 0.346%

    No Known Activations