© 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. 110988
    Prev
    Next
    INDEX
    Explanations

    code separators and namespaces

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

    This neuron detects license‐header boilerplate tokens (e.g. copyright notices, version numbers, “Licensed under … Version,” URLs).

    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
     SF
    -0.87
    敖
    -0.85
    eventbus
    -0.75
     thành
    -0.75
    closures
    -0.72
    avaj
    -0.72
     enclosure
    -0.71
     sf
    -0.71
    сказа
    -0.70
    xvii
    -0.70
    POSITIVE LOGITS
    ึง
    0.83
     XLS
    0.80
     rifi
    0.77
     gradualmente
    0.74
     Highlander
    0.73
     strug
    0.73
    umal
    0.72
     Waterways
    0.72
    XLS
    0.72
    Heard
    0.72
    Activations Density 0.059%

    No Known Activations