© 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. 1444
    Prev
    Next
    INDEX
    Explanations

    work or construction beginning

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

    The neuron activates on numeric expressions (digits, years, measurements) 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
     wants
    -1.35
     if
    -1.35
     uses
    -1.34
    那些
    -1.32
    </h3>
    -1.30
    $,
    -1.29
     those
    -1.28
    '],$
    -1.28
     both
    -1.27
    annia
    -1.26
    POSITIVE LOGITS
     rimane
    1.41
    意外と
    1.36
    你这
    1.35
     ebbe
    1.34
    ーズン
    1.32
     amazingly
    1.31
    okohama
    1.30
    蛱
    1.30
    一个小
    1.30
    ataires
    1.28
    Activations Density 0.053%

    No Known Activations