© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63423
    Prev
    Next
    INDEX
    Explanations

    Ripely Pine, Neurohormones, different city

    np_acts-logits-general · gemini-2.5-flash-lite

    cloud computing and AWS (Amazon Web Services) related technical terminology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly responds to AWS/EKS (or kops) network‐topology and VPC internal networking option tokens—i.e. words that name private/internal networking or VPC flags.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Naomi
    -0.76
    ıldız
    -0.75
     сда
    -0.74
    ૂ
    -0.73
     goes
    -0.72
    沙发
    -0.71
    ulative
    -0.71
     Ever
    -0.71
    ншни
    -0.70
    sima
    -0.70
    POSITIVE LOGITS
     bastion
    0.97
     peered
    0.86
    sg
    0.82
    pecker
    0.81
     Networking
    0.81
    SG
    0.81
     VPC
    0.81
     network
    0.78
    Networking
    0.77
     recreated
    0.77
    Activations Density 0.046%

    No Known Activations