© 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. 68368
    Prev
    Next
    INDEX
    Explanations

    units of measurement quantities

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

    The neuron triggers on numeric measurements (numbers often paired with units) in scientific 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
     is
    -1.31
     weiteren
    -1.20
    ↵↵
    -1.10
    以外
    -1.10
     isn
    -1.09
    Otra
    -1.07
    autres
    -1.02
    gnąć
    -1.01
     otros
    -0.98
     further
    -0.98
    POSITIVE LOGITS
    laşı
    1.34
    andingan
    1.25
     suéter
    1.23
     lavado
    1.22
     Francus
    1.21
    ipzig
    1.18
     gorro
    1.17
    laştır
    1.16
     quà
    1.14
     diciembre
    1.12
    Activations Density 0.070%

    No Known Activations