© 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. 22-GEMMASCOPE-RES-131K
    7. 131038
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens—i.e. any token containing digits or numeric values.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    Switzerland language codes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    本体
    -1.06
     itself
    -1.05
    本身
    -1.03
    actual
    -0.95
     بالفعل
    -0.95
    main
    -0.94
     actual
    -0.92
     ACTUAL
    -0.90
     eigentlichen
    -0.88
    普通に
    -0.84
    POSITIVE LOGITS
    closeup
    0.93
    THIRD
    0.91
     third
    0.87
     Another
    0.84
    inerario
    0.83
    ± 
    0.80
     another
    0.77
     accommodating
    0.77
     princesse
    0.77
    COMO
    0.77
    Activations Density 0.065%

    No Known Activations