© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31715
    Prev
    Next
    INDEX
    Explanations

    network requests and responses

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

    The neuron detects Java/Android source‐code tokens—especially punctuation (., ;, _, etc.) and keywords in import and class/method definitions.

    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
     mondial
    -0.86
     报
    -0.83
    CultureInfo
    -0.82
     ventes
    -0.81
     ekster
    -0.80
    🤳
    -0.80
     industrielle
    -0.79
     arbre
    -0.78
     jupe
    -0.77
     porcelaine
    -0.77
    POSITIVE LOGITS
     response
    1.16
     network
    1.12
     net
    0.97
     responses
    0.92
     request
    0.92
     networks
    0.84
    networking
    0.83
     deliver
    0.82
     Net
    0.81
    pastebin
    0.81
    Activations Density 0.007%

    No Known Activations