© 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. 109101
    Prev
    Next
    INDEX
    Explanations

    random number 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_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
     randomly
    -1.48
    random
    -1.40
     random
    -1.36
    随机
    -1.17
    Random
    -1.05
     Random
    -0.98
    RANDOM
    -0.94
     RANDOM
    -0.93
     randomness
    -0.84
     arbitrary
    -0.75
    POSITIVE LOGITS
     PR
    0.90
     mt
    0.88
     MT
    0.83
    伪
    0.82
    secure
    0.80
    PR
    0.79
     mers
    0.79
    Secure
    0.77
     Mers
    0.77
    MERS
    0.76
    Activations Density 0.027%

    No Known Activations