© 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. 90565
    Prev
    Next
    INDEX
    Explanations

    shell commands and scripts

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

    The neuron detects numeric literals (including integers and decimals) 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
    戆
    -1.84
     they
    -1.80
     have
    -1.79
    ୪
    -1.73
     is
    -1.73
    聼
    -1.73
     about
    -1.69
     purported
    -1.65
     могут
    -1.62
    ная
    -1.60
    POSITIVE LOGITS
    рення
    1.81
     chaque
    1.57
    (
    1.54
     glede
    1.48
     navigu
    1.41
     Gór
    1.39
     esso
    1.37
    ization
    1.36
     roasting
    1.35
     grilling
    1.35
    Activations Density 0.008%

    No Known Activations