© 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. 35159
    Prev
    Next
    INDEX
    Explanations

    returned or removed after a period

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

    The neuron activates on numeric expressions (numbers, measurements, and statistical values) 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
    begins
    -1.08
    琚
    -0.98
     inizia
    -0.92
     يريد
    -0.90
     olmuş
    -0.89
     بدأ
    -0.89
     vandens
    -0.88
    mesine
    -0.86
    documentclass
    -0.85
    nuevos
    -0.85
    POSITIVE LOGITS
     eventually
    1.77
     later
    1.38
     eventual
    1.37
    Eventually
    1.27
     Eventually
    1.26
    eventually
    1.23
     eventualmente
    1.14
     after
    1.12
     if
    1.09
     someday
    1.05
    Activations Density 0.027%

    No Known Activations