© 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. 10-GEMMASCOPE-RES-131K
    7. 128969
    Prev
    Next
    INDEX
    Explanations

    energy efficiency and conservation

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

    The neuron fires on mentions of energy‐efficiency concepts, especially the phrase “energy efficiency” or related terms describing measures or policies to improve energy use.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    indeed
    -1.41
    SOME
    -1.36
    whose
    -1.34
    hability
    -1.30
    ᥬ
    -1.27
    however
    -1.23
    🖼
    -1.23
    needed
    -1.23
     NSCoder
    -1.23
    隐隐
    -1.22
    POSITIVE LOGITS
     things
    1.46
     how
    1.45
     more
    1.39
     aspects
    1.36
    szön
    1.24
     would
    1.23
     when
    1.23
     including
    1.20
     megane
    1.19
     and
    1.16
    Activations Density 0.039%

    No Known Activations