© 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. 90975
    Prev
    Next
    INDEX
    Explanations

    client initialization or endpoint specific

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

    The neuron detects domain-based module import path segments (e.g. GitHub repository URLs) in Go-style import strings.

    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
     immense
    -0.82
    WHE
    -0.81
     Netzwerk
    -0.79
    uL
    -0.77
    IBS
    -0.75
    nique
    -0.75
     sĩ
    -0.74
    alable
    -0.73
     mẹ
    -0.72
     fertile
    -0.72
    POSITIVE LOGITS
     client
    2.14
     clients
    1.86
    client
    1.68
    Client
    1.63
    CLIENT
    1.52
     Client
    1.42
    客户端
    1.38
     klien
    1.35
    ServiceClient
    1.34
    クライ
    1.30
    Activations Density 0.056%

    No Known Activations