© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47147
    Prev
    Next
    INDEX
    Explanations

    control and status registers

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

    The neuron strongly activates on code identifiers and declarations involving registers (e.g. “register,” register-access types, register count constants, etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     duelo
    -0.87
     équilibr
    -0.84
    歌词
    -0.76
     Enkel
    -0.75
    asgi
    -0.72
     atleta
    -0.72
     Erfol
    -0.72
     Kompon
    -0.71
     normalen
    -0.71
     citar
    -0.70
    POSITIVE LOGITS
    control
    1.73
     Control
    1.66
     control
    1.66
     CONTROL
    1.48
    Control
    1.48
    CONTROL
    1.42
    status
    1.41
     status
    1.37
    ctrl
    1.22
     Status
    1.20
    Activations Density 0.017%

    No Known Activations