© 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. 6917
    Prev
    Next
    INDEX
    Explanations

    cloud resource deployment

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

    The neuron primarily responds to code or configuration syntax—especially identifiers, keywords, and structured fields in scripts or JSON/ARM‐template snippets.

    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
     живе
    -0.88
    DRA
    -0.86
     EDM
    -0.81
     tää
    -0.77
     DRA
    -0.75
    mbh
    -0.75
     Supplementary
    -0.75
    Edm
    -0.75
     Draper
    -0.75
     江
    -0.74
    POSITIVE LOGITS
     subscription
    1.18
    Subscription
    1.05
     subscriptions
    0.99
    subscription
    0.96
     Subscription
    0.92
    公寓
    0.81
     Subscriptions
    0.77
     deployment
    0.76
     afficher
    0.74
     spending
    0.74
    Activations Density 0.046%

    No Known Activations