© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30383
    Prev
    Next
    INDEX
    Explanations

    math and time functions

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

    This neuron detects references to math libraries or their functions (e.g. “<cmath>,” “math,” “sqrt,” “log”).

    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
    Buffer
    -0.80
     parseInt
    -0.79
     Buffer
    -0.78
    وید
    -0.78
    Integer
    -0.77
    parseInt
    -0.76
     Integer
    -0.75
    機の
    -0.74
    Alice
    -0.73
    Rotate
    -0.73
    POSITIVE LOGITS
     fabs
    1.58
    fabs
    1.54
     fab
    1.15
     Fab
    0.94
    FAB
    0.91
    več
    0.90
     floor
    0.88
    fab
    0.88
     FAB
    0.85
    Lebih
    0.82
    Activations Density 0.019%

    No Known Activations