© 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. 83175
    Prev
    Next
    INDEX
    Explanations

    gpu hardware

    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
     くる
    -0.71
     transmiti
    -0.71
    ]_{\
    -0.70
    bundled
    -0.69
    quine
    -0.68
    toByteArray
    -0.68
    isis
    -0.68
    FTP
    -0.68
     Eup
    -0.67
     Basis
    -0.66
    POSITIVE LOGITS
     GPU
    1.55
     gpu
    1.51
     GPUs
    1.42
     devices
    1.41
    gpu
    1.41
     device
    1.36
     CUDA
    1.16
     cards
    1.07
     NVIDIA
    1.07
    GPU
    1.06
    Activations Density 0.026%

    No Known Activations