© 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. 84545
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations

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

    The neuron detects numeric constants (numbers) in 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
     which
    -0.91
    用戶
    -0.90
     beweisen
    -0.89
     many
    -0.85
     hampir
    -0.82
     многих
    -0.81
     díky
    -0.80
     we
    -0.79
     rascal
    -0.79
     Чтобы
    -0.78
    POSITIVE LOGITS
    izat
    1.21
    rrbracket
    1.02
    厚度
    0.96
    voyez
    0.94
    ־ה
    0.93
     vertus
    0.91
    perity
    0.90
     ruban
    0.90
    TreeNode
    0.90
    institutions
    0.88
    Activations Density 0.001%

    No Known Activations