© 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. 64101
    Prev
    Next
    INDEX
    Explanations

    peak electricity demand

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

    The neuron activates on numeric tokens, i.e. any standalone numbers or digits in the text.

    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
     塩
    -0.84
    蒴
    -0.78
     scribe
    -0.78
     Kode
    -0.77
     conclud
    -0.77
    ljiv
    -0.76
     workman
    -0.76
    atória
    -0.74
    東大
    -0.74
     statistique
    -0.74
    POSITIVE LOGITS
     peak
    1.66
     electricity
    1.34
     Peak
    1.31
    peak
    1.30
     peaks
    1.27
    Peak
    1.18
     usage
    1.14
     load
    1.07
     demand
    1.06
     consumption
    1.06
    Activations Density 0.015%

    No Known Activations