© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 129081
    Prev
    Next
    INDEX
    Explanations

    server systems and networking

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

    The neuron fires on technical infrastructure terms describing storage systems, nodes, clusters, controllers, redundancy, and failover.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     EVEN
    -1.47
    𝑈
    -1.45
     Mbappe
    -1.42
    набор
    -1.28
     Ouvrez
    -1.27
      [
    -1.27
    Viited
    -1.26
     aktualisiert
    -1.25
     élar
    -1.25
     Debido
    -1.23
    POSITIVE LOGITS
     like
    1.45
     so
    1.40
     your
    1.34
     then
    1.29
    ,
    1.22
     without
    1.19
     at
    1.12
    }\}
    1.09
     of
    1.09
     from
    1.09
    Activations Density 0.328%

    No Known Activations