© 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. 34-GEMMASCOPE-RES-131K
    7. 76127
    Prev
    Next
    INDEX
    Explanations

    India, Head, AstraZeneca, KY

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

    The neuron strongly activates on numeric tokens (e.g. years, counts, IDs) wherever they appear.

    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
     their
    -1.34
     like
    -1.16
     parecen
    -0.88
     in
    -0.85
    สูง
    -0.83
     by
    -0.82
     while
    -0.82
     сал
    -0.80
    urop
    -0.79
     TÉCN
    -0.78
    POSITIVE LOGITS
     toutefois
    1.15
     ügy
    0.95
     áng
    0.92
     zwięks
    0.91
     делает
    0.88
     vstup
    0.88
     şöyle
    0.87
     våra
    0.87
    私も
    0.85
    ↵
    0.85
    Activations Density 0.001%

    No Known Activations