© 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. 107556
    Prev
    Next
    INDEX
    Explanations

    post-installation configuration options

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

    The neuron activates on the boilerplate header lines of source files—especially license, copyright, and project‐metadata tokens.

    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
    ственно
    -0.79
     Bellini
    -0.77
    raison
    -0.77
    𝘇
    -0.73
    CHRE
    -0.72
    cleo
    -0.71
    锁定
    -0.71
     그것
    -0.68
    bahn
    -0.68
    ciatore
    -0.68
    POSITIVE LOGITS
    Item
    1.34
     Item
    1.21
    task
    1.16
     task
    1.06
    option
    1.04
    Task
    1.01
    component
    0.93
     component
    0.87
     Component
    0.85
     TASK
    0.84
    Activations Density 0.020%

    No Known Activations