© 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. 76111
    Prev
    Next
    INDEX
    Explanations

    opening times, Bloody Spear, Regional anesthesia

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

    The neuron strongly activates on configuration and deployment terminology—tokens like “Configuring,” “Service,” “environment,” “CAS,” back‐ticks and hyphens—that appear in technical docs or code snippets describing service/environment setup.

    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
    bida
    -0.88
    UnifiedTopology
    -0.79
    osamente
    -0.72
     QuickBooks
    -0.70
     BP
    -0.70
    ERD
    -0.69
    vsk
    -0.69
    astă
    -0.69
    nungs
    -0.68
    鲨
    -0.68
    POSITIVE LOGITS
    institution
    0.79
     cas
    0.79
     athletics
    0.78
    Iowa
    0.77
    見到
    0.77
     schwed
    0.77
     uman
    0.76
    vidade
    0.76
    codehaus
    0.74
    влению
    0.74
    Activations Density 0.007%

    No Known Activations