© 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. 22-GEMMASCOPE-RES-131K
    7. 79595
    Prev
    Next
    INDEX
    Explanations

    cloud configuration parameters

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

    The neuron strongly activates on cloud/cluster networking setup keywords—especially terms like “private,” “topology,” “internal,” “load balancer,” and related infrastructure configuration words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     katholischen
    -1.44
    肄
    -1.34
    ֺ
    -1.32
     trover
    -1.32
     tristes
    -1.32
     valore
    -1.32
     MANY
    -1.30
     evtl
    -1.30
     Pfar
    -1.28
    ⠐
    -1.28
    POSITIVE LOGITS
     your
    1.80
    וּ
    1.59
     Администра
    1.39
     сериал
    1.34
    ҉
    1.33
     получите
    1.32
     бампер
    1.30
     vaše
    1.28
     Sécurité
    1.27
    ınıza
    1.27
    Activations Density 0.054%

    No Known Activations