© 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. 10-GEMMASCOPE-RES-131K
    7. 104095
    Prev
    Next
    INDEX
    Explanations

    fuel economy and MPG

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

    The neuron detects mentions of fuel‐related performance metrics (e.g. fuel economy, fuel consumption, or fuel efficiency figures).

    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
    そういえば
    -1.42
     évident
    -1.20
    ↵
    -1.20
     similares
    -1.20
     époux
    -1.17
     Weltkrieg
    -1.17
     generalised
    -1.17
     ALSO
    -1.16
    どうやら
    -1.16
     of
    -1.16
    POSITIVE LOGITS
     you
    1.80
     garantis
    1.33
    cual
    1.30
    嵛
    1.27
     餐厅
    1.27
     vittoria
    1.26
     любой
    1.24
     only
    1.24
    了几
    1.24
    atever
    1.22
    Activations Density 0.018%

    No Known Activations