© 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. 129709
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to numeric tokens (measurements, chart values, and other numbers).

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

    left, right, and positions

    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
     şeyi
    -1.06
     reveló
    -1.01
     öner
    -0.94
     mason
    -0.92
    athan
    -0.91
    ляют
    -0.90
    AlreadyExists
    -0.90
    iscono
    -0.89
    Would
    -0.87
    了什么
    -0.86
    POSITIVE LOGITS
     first
    1.17
     blue
    1.16
     left
    0.97
     bold
    0.94
     orange
    0.94
     their
    0.94
     here
    0.92
     indicated
    0.90
     generously
    0.90
    sillon
    0.89
    Activations Density 0.017%

    No Known Activations