© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 66040
    Prev
    Next
    INDEX
    Explanations

    variable assignment or section title

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

    The neuron fires on occurrences of the identifier “process” (in any casing) in code, especially in CMS configuration scripts.

    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
    ront
    -0.78
    Value
    -0.76
     entity
    -0.73
    Entity
    -0.73
     Registry
    -0.71
    CREATED
    -0.71
     Москве
    -0.71
     ataca
    -0.69
     Савез
    -0.69
    Sim
    -0.68
    POSITIVE LOGITS
    Monarch
    0.66
    owels
    0.65
     relive
    0.63
    正規
    0.61
     उच्च
    0.61
    Enigma
    0.60
     مجموعه
    0.60
     Benedikt
    0.59
     Monarch
    0.59
     Toggle
    0.59
    Activations Density 0.059%

    No Known Activations