© 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. 22-GEMMASCOPE-RES-131K
    7. 27689
    Prev
    Next
    INDEX
    Explanations

    differential calculus, mathematical notation

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

    The neuron fires on numeric tokens—i.e. it detects occurrences of numbers (digits or multi-digit numerals) 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_22/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
    imbang
    -0.91
     旅游
    -0.89
     too
    -0.89
    Nieuw
    -0.88
    silla
    -0.84
     known
    -0.83
     setzte
    -0.81
     sodio
    -0.81
    nhung
    -0.80
    marzo
    -0.80
    POSITIVE LOGITS
     Buffalo
    0.85
     partout
    0.83
     autour
    0.82
    Buffalo
    0.81
    Text
    0.78
    Bru
    0.77
     照明
    0.75
     шкаф
    0.75
     lokal
    0.74
    までも
    0.74
    Activations Density 0.009%

    No Known Activations