© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 35566
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code snippets

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

    The neuron is keyed to spotting mathematical expressions involving exponentiation (e.g. “**”, power terms, “Simplify(…)”).

    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
     généraux
    -1.23
     continue
    -1.14
     ofrecen
    -1.10
    来讲
    -1.06
     correctes
    -1.06
     完了
    -1.05
     Blocks
    -1.03
     improve
    -1.02
     intrinsically
    -1.02
    b
    -1.02
    POSITIVE LOGITS
    ——”
    1.34
    ......”
    1.26
     répon
    1.23
     découv
    1.20
     venga
    1.19
     tomen
    1.18
    鰨
    1.17
    afternoon
    1.16
     sette
    1.15
     escenas
    1.13
    Activations Density 34.824%

    No Known Activations