© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82787
    Prev
    Next
    INDEX
    Explanations

    DC and AC power adapters

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

    The neuron fires on mentions of electrical power specifications—especially voltage, power supply, and related numeric units.

    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
    density
    -0.79
    ssos
    -0.77
     olabilir
    -0.77
    accessible
    -0.74
    dword
    -0.74
     gossi
    -0.73
    poran
    -0.71
     density
    -0.71
    icate
    -0.69
     bản
    -0.69
    POSITIVE LOGITS
     DC
    1.35
    DC
    1.16
     dc
    0.99
     regulated
    0.98
     output
    0.97
     barrel
    0.94
    dc
    0.93
     Barrel
    0.91
     unregulated
    0.85
    barrel
    0.84
    Activations Density 0.030%

    No Known Activations