© 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. 75500
    Prev
    Next
    INDEX
    Explanations

    http urls and network addresses

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

    The neuron strongly responds to TypeScript/Angular code tokens (e.g. “import,” braces, “Component,” “View,” etc.), effectively detecting snippets of Angular‐style code.

    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
    клар
    -0.84
    CBS
    -0.82
     impug
    -0.80
     Guatemala
    -0.80
     GHS
    -0.77
     PHE
    -0.77
     ibland
    -0.76
     zaterdag
    -0.75
     她
    -0.75
    брав
    -0.75
    POSITIVE LOGITS
     zima
    0.88
     LIMITS
    0.75
     colorir
    0.74
     binding
    0.74
    binding
    0.74
    lück
    0.73
    🧃
    0.73
    horst
    0.73
    aptors
    0.73
    暟
    0.72
    Activations Density 0.005%

    No Known Activations