© 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. 59003
    Prev
    Next
    INDEX
    Explanations

    nvidia CUDA

    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
     Sony
    -0.72
     DNA
    -0.69
     often
    -0.69
    amil
    -0.68
    тия
    -0.68
     MTV
    -0.68
     frío
    -0.68
     Chelsea
    -0.67
     Bosch
    -0.67
     PlayStation
    -0.66
    POSITIVE LOGITS
     nv
    1.23
     GeForce
    1.22
     cuda
    1.18
     CUDA
    1.11
    NV
    1.08
     NV
    1.05
     nvidia
    1.04
    cuda
    1.02
    NVIDIA
    1.00
    Nv
    0.99
    Activations Density 0.064%

    No Known Activations