© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91669
    Prev
    Next
    INDEX
    Explanations

    quantities, comparisons, and degree

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

    This neuron activates primarily on numerical tokens or number-like expressions (e.g., digits, counts, statistics).

    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
    iciais
    -0.96
    ђу
    -0.95
    ceiro
    -0.94
    itext
    -0.93
    Horário
    -0.91
     BrowserRouter
    -0.91
    گانه
    -0.91
    vateľov
    -0.90
     verp
    -0.90
    ξύ
    -0.90
    POSITIVE LOGITS
     more
    7.00
    more
    4.28
     więcej
    4.03
     больше
    3.83
     più
    3.75
     більше
    3.59
     lebih
    3.55
     повече
    3.50
     mehr
    3.50
    More
    3.48
    Activations Density 0.166%

    No Known Activations