© 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. 652
    Prev
    Next
    INDEX
    Explanations

    voltage levels and supplies

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

    This neuron responds strongly to numeric tokens—especially quantitative values like voltages, currents, and other specification numbers.

    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
    ctiveness
    -0.95
    ватися
    -0.75
    ၢ
    -0.75
    grafen
    -0.74
     Sö
    -0.73
     sopa
    -0.73
     sauna
    -0.72
     pâte
    -0.71
    RDS
    -0.71
    фей
    -0.71
    POSITIVE LOGITS
     supply
    1.55
    supply
    1.16
    Supply
    1.13
     Supply
    1.11
     SUPPLY
    0.97
     V
    0.96
     rail
    0.95
     supplies
    0.93
     suppliers
    0.92
    REF
    0.91
    Activations Density 0.044%

    No Known Activations