© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107864
    Prev
    Next
    INDEX
    Explanations

    DC/AC electrical power

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

    The neuron activates on references to electrical current types (e.g. “DC,” “AC,” and related abbreviations).

    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
    ichte
    -0.80
    へ行
    -0.79
    tutor
    -0.78
     Einige
    -0.74
    zyme
    -0.73
     angels
    -0.73
    ths
    -0.73
     ossia
    -0.73
    鼓励
    -0.71
    mming
    -0.70
    POSITIVE LOGITS
     DC
    1.59
    DC
    1.28
    dc
    1.27
     AC
    1.13
    Dc
    0.97
    DCs
    0.95
    AC
    0.93
     power
    0.90
     dc
    0.90
     hip
    0.83
    Activations Density 0.029%

    No Known Activations