© 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. 90931
    Prev
    Next
    INDEX
    Explanations

    voltage circuit discussion

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     funcionarios
    -1.00
     verst
    -0.94
     erns
    -0.93
     struk
    -0.92
     modalités
    -0.91
    >("
    -0.91
    daction
    -0.90
    truct
    -0.90
     collega
    -0.90
    kilometer
    -0.90
    POSITIVE LOGITS
     voltage
    1.52
     circuit
    1.40
     parasitic
    1.21
     voltages
    1.16
     Spice
    1.14
    voltage
    1.11
     Circuit
    1.09
     datasheet
    1.07
     Bias
    1.07
     output
    1.06
    Activations Density 0.138%

    No Known Activations