© 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. 81744
    Prev
    Next
    INDEX
    Explanations

    gpu on devices

    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
     incipient
    -0.79
    会出现
    -0.75
    Alternatives
    -0.73
     parentage
    -0.71
     его
    -0.70
    一等
    -0.69
    inely
    -0.69
    Ừ
    -0.68
     whiteboard
    -0.68
    нология
    -0.68
    POSITIVE LOGITS
     device
    2.50
     devices
    2.25
    device
    2.16
     Device
    1.84
     DEVICE
    1.82
    DEVICE
    1.80
    Device
    1.79
     Devices
    1.69
    devices
    1.49
    getDevice
    1.46
    Activations Density 0.003%

    No Known Activations