© 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. 31707
    Prev
    Next
    INDEX
    Explanations

    electricity supply and costs

    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
     grø
    -0.85
    Carpet
    -0.83
     Donaldson
    -0.82
    🫕
    -0.79
     Carpet
    -0.78
     RESOURCE
    -0.77
    dera
    -0.76
     adat
    -0.75
     Resource
    -0.73
    ilingual
    -0.73
    POSITIVE LOGITS
     meter
    1.26
     consumers
    1.12
     supply
    1.04
     Meter
    1.02
     electricity
    1.02
     substation
    1.01
     distribution
    0.99
     transformer
    0.98
     metering
    0.98
     meters
    0.97
    Activations Density 0.011%

    No Known Activations