© 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. 21722
    Prev
    Next
    INDEX
    Explanations

    links to articles or sites

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

    The neuron strongly activates on numeric tokens—i.e. sequences of digits (dates, IDs, counts) rather than words.

    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
     to
    -1.95
    o
    -1.66
    _
    -1.66
    `
    -1.47
    end
    -1.45
    着一个
    -1.41
    g
    -1.40
     passieren
    -1.38
    ’
    -1.38
     ähnlichen
    -1.37
    POSITIVE LOGITS
     vendeurs
    1.63
    continu
    1.62
    盌
    1.56
     victoires
    1.56
    窣
    1.55
     mères
    1.52
    颪
    1.48
     acheteurs
    1.46
    歟
    1.45
     venuto
    1.44
    Activations Density 0.025%

    No Known Activations