© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13703
    Prev
    Next
    INDEX
    Explanations

    electricity, gas, utility billing

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

    The neuron reliably fires on numerical and quantitative tokens—i.e. digits, measurements, and other numeric data in text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⛴
    0.58
     мор
    0.57
    öra
    0.55
     absolv
    0.55
     seaport
    0.55
     distiller
    0.53
     biosynthesis
    0.52
    rypsin
    0.52
    🏁
    0.52
     FHWA
    0.52
    POSITIVE LOGITS
     electricity
    1.52
     meter
    1.52
    Electricity
    1.50
     Electricity
    1.48
     utility
    1.47
    electricity
    1.43
     Utility
    1.42
    Utility
    1.38
     Meter
    1.38
     utilities
    1.37
    Activations Density 0.334%

    No Known Activations