© 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. 75466
    Prev
    Next
    INDEX
    Explanations

    corresponding

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

    The neuron detects numeric values and measurements (e.g. integers and decimals) 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
    minton
    -1.55
     bouteilles
    -1.31
     piattaforma
    -1.29
    ständige
    -1.28
     dipu
    -1.28
    issement
    -1.28
    ครื่อง
    -1.27
    ㈯
    -1.26
    킁
    -1.25
    
    -1.23
    POSITIVE LOGITS
     their
    1.45
     which
    1.36
     that
    1.34
     provide
    1.23
     serves
    1.16
     E
    1.13
     provides
    1.12
     ў
    1.12
     with
    1.11
     Providing
    1.11
    Activations Density 0.081%

    No Known Activations