© 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. 34-GEMMASCOPE-RES-131K
    7. 34738
    Prev
    Next
    INDEX
    Explanations

    programming language constructs

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

    The neuron consistently responds to numeric tokens (digits or number literals) in 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_34/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
    Phillips
    -0.89
     Scotts
    -0.80
    Yet
    -0.76
    hist
    -0.74
     ета
    -0.73
     Uzbekistan
    -0.73
    定时
    -0.72
    roquia
    -0.71
     flexing
    -0.70
    網友
    -0.70
    POSITIVE LOGITS
     infeliz
    0.88
    colgroup
    0.84
    Mutex
    0.79
    тр
    0.77
    Bris
    0.77
    ჩ
    0.77
    bouw
    0.77
    ống
    0.77
     rpc
    0.76
    ˝
    0.75
    Activations Density 0.003%

    No Known Activations