© 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. 105322
    Prev
    Next
    INDEX
    Explanations

    listing supplementary items

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

    The neuron consistently activates on standalone numeric tokens (e.g. “364”, “360”, “358”), i.e. it’s detecting numbers.

    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
     if
    -2.52
     only
    -2.30
     multitude
    -2.11
     more
    -2.05
    ↵↵
    -2.05
     remainder
    -2.02
     possibility
    -2.00
     in
    -1.98
     same
    -1.95
     even
    -1.90
    POSITIVE LOGITS
    ครื่อง
    2.45
    焢
    2.19
    嵎
    2.17
    趼
    1.98
    苳
    1.98
    鮡
    1.97
    ก่อน
    1.95
    獁
    1.93
    ᠁
    1.91
     kurios
    1.91
    Activations Density 0.009%

    No Known Activations