© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92342
    Prev
    Next
    INDEX
    Explanations

    media access control

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

    The neuron fires on specialized networking-and-communication protocol terms and jargon (e.g. control, allocation, priority, PHY/MAC layer terminology).

    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
    routed
    -0.92
    ÊNCIAS
    -0.85
    requently
    -0.73
     SSE
    -0.73
    getLabel
    -0.73
    ACTED
    -0.72
    płat
    -0.72
    konen
    -0.71
    SSE
    -0.71
    ทีม
    -0.70
    POSITIVE LOGITS
     access
    1.55
     Access
    1.55
    Access
    1.41
    access
    1.40
     collisions
    1.29
     Collision
    1.25
     MAC
    1.23
    Collision
    1.20
     collision
    1.20
    collision
    1.18
    Activations Density 0.079%

    No Known Activations