© 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. 65835
    Prev
    Next
    INDEX
    Explanations

    register definitions

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

    The neuron predominantly fires on uppercase hardware or register identifiers (e.g. register names, control/enable flags) in code.

    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
     entertaining
    -0.71
     cic
    -0.71
     arranged
    -0.71
     interrupts
    -0.70
     reduced
    -0.68
    つけた
    -0.67
     think
    -0.66
    читься
    -0.66
    weebly
    -0.66
     extro
    -0.66
    POSITIVE LOGITS
    ordat
    0.86
     carros
    0.85
     EPISODE
    0.83
    MetaObject
    0.83
     matiz
    0.82
    essed
    0.78
    踊
    0.78
     koncer
    0.77
    棪
    0.77
    tivität
    0.77
    Activations Density 0.010%

    No Known Activations