© 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. 95770
    Prev
    Next
    INDEX
    Explanations

    parentheses and mathematical symbols

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

    The neuron is detecting multiplication operations (the “*” symbols) within mathematical expressions.

    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
    cuits
    -1.10
    solete
    -1.00
     terça
    -0.98
    篭
    -0.96
     事業
    -0.96
     predic
    -0.96
     як
    -0.94
    ensin
    -0.93
     quiso
    -0.93
    caman
    -0.93
    POSITIVE LOGITS
     eerste
    1.23
     uiteindelijk
    0.91
    RIQUE
    0.90
     mariée
    0.90
     ""],
    0.88
    𝐅
    0.87
    れました
    0.86
    짬
    0.85
     armée
    0.83
    #{
    0.82
    Activations Density 0.012%

    No Known Activations