© 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. 34-GEMMASCOPE-RES-131K
    4. 50011
    Prev
    Next
    INDEX
    Explanations

    mathematical coefficients and equations

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

    The neuron activates on numeric tokens and mathematical numerals (e.g., digits, equation numbers, and other number‐related 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_34/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
     blobs
    -0.69
     anything
    -0.67
     inbound
    -0.66
    ErrMsg
    -0.66
    ondas
    -0.66
    թ
    -0.65
    quini
    -0.65
    Modifiers
    -0.64
     Sonntag
    -0.64
     flatten
    -0.64
    POSITIVE LOGITS
     div
    0.81
     воспользоваться
    0.78
    ísa
    0.76
     coefficients
    0.76
     heated
    0.75
    ceived
    0.75
    heated
    0.75
     Pala
    0.73
     Dri
    0.72
    DIV
    0.72
    Activations Density 0.039%

    No Known Activations