© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130522
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to references to randomness—tokens like “random,” “rand,” “randint,” and “randomly.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    random selection and generation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    íveis
    -0.96
     område
    -0.96
     fhort
    -0.94
    ORANGE
    -0.94
     lepro
    -0.90
    warzys
    -0.90
     naran
    -0.89
    Lø
    -0.88
    λαν
    -0.87
    클
    -0.86
    POSITIVE LOGITS
     random
    1.87
    random
    1.59
     randomly
    1.53
    随机
    1.52
     RANDOM
    1.52
     randomness
    1.48
     chance
    1.39
    Random
    1.37
    srand
    1.25
     randomized
    1.22
    Activations Density 0.134%

    No Known Activations