© 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. 102510
    Prev
    Next
    INDEX
    Explanations

    register or registers

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

    This neuron specializes in spotting mentions or definitions of processor registers (e.g. the word “register” or register‐related macros) in code and technical text.

    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
     boost
    -0.81
     branch
    -0.79
    branch
    -0.74
    基本上
    -0.73
    コーチ
    -0.72
     always
    -0.71
    inov
    -0.70
     Mullins
    -0.70
    鹹
    -0.69
     מא
    -0.68
    POSITIVE LOGITS
     register
    1.55
     registers
    1.40
     Register
    1.33
    Register
    1.23
    register
    1.21
     Registers
    1.11
     registro
    1.08
    Registers
    1.05
     reg
    1.02
    RegisterType
    1.00
    Activations Density 0.032%

    No Known Activations