© 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. 34-GEMMASCOPE-RES-131K
    7. 7992
    Prev
    Next
    INDEX
    Explanations

    mathematical matrices

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

    The neuron fires on technical/mathematical code and discussion—especially linear‐algebra or matrix‐operation contexts (e.g. function definitions like “def recurrence,” calls like “T.dot,” “tanh,” and discussions of matrices/operators).

    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
    INGO
    -0.76
    forRoot
    -0.75
    medriver
    -0.72
    Duplicates
    -0.71
    azole
    -0.71
     Мен
    -0.70
    LoginActivity
    -0.70
     approximations
    -0.70
     DIY
    -0.69
    bootstrapcdn
    -0.69
    POSITIVE LOGITS
     matrix
    2.33
     матри
    1.96
    matrix
    1.84
    Matrix
    1.84
    矩阵
    1.81
     Matrix
    1.78
    matmul
    1.63
     matrices
    1.55
     matri
    1.39
     Matrices
    1.35
    Activations Density 0.041%

    No Known Activations