© 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. 79546
    Prev
    Next
    INDEX
    Explanations

    physics and technical terms

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

    The neuron activates on numeric tokens and mathematical equation elements (e.g. numbers, operators, coefficients, and variable symbols) in 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
     to
    -1.27
     katun
    -1.22
     kuv
    -1.08
     puo
    -1.07
     německ
    -1.06
     volverá
    -1.05
    iconos
    -1.02
     Masalah
    -1.01
    Questão
    -1.00
    🦝
    -0.96
    POSITIVE LOGITS
    =()=>{
    1.08
    Cow
    1.01
     both
    0.94
    岛
    0.94
     láp
    0.93
     uñas
    0.93
     télécommande
    0.92
     dientes
    0.92
    ۶
    0.91
    买
    0.88
    Activations Density 0.003%

    No Known Activations