© 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. 90572
    Prev
    Next
    INDEX
    Explanations

    package main import

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

    The neuron detects numeric literals (integer and floating-point numbers) in code.

    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
    </strong>
    -1.41
     "
    -1.41
    </sup>
    -1.38
    了个
    -1.33
    actory
    -1.32
     促销
    -1.32
    REACT
    -1.31
    ety
    -1.30
     Keine
    -1.30
    RAH
    -1.30
    POSITIVE LOGITS
     /**
    1.56
    slavery
    1.31
    értelmű
    1.31
    abancı
    1.29
     voordelen
    1.25
     kılıf
    1.21
    ของ
    1.21
    shat
    1.20
    rainy
    1.20
     baskılı
    1.20
    Activations Density 0.012%

    No Known Activations