© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1371
    Prev
    Next
    INDEX
    Explanations

    creating rules and policies

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

    This neuron fires on programming identifiers—especially CamelCase or other code symbols like function, type, and pipeline names.

    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
    AccountNumber
    -0.90
    StateChange
    -0.86
    hac
    -0.85
    liziert
    -0.85
    ánk
    -0.83
    TypeMap
    -0.83
    Ⓔ
    -0.83
     Swedish
    -0.82
    ῖς
    -0.81
    搅拌
    -0.80
    POSITIVE LOGITS
     name
    1.87
     created
    1.61
     saved
    1.52
    名称
    1.35
     copied
    1.34
     copy
    1.33
     creation
    1.32
    name
    1.30
    Created
    1.27
     созда
    1.27
    Activations Density 0.056%

    No Known Activations