© 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. 12633
    Prev
    Next
    INDEX
    Explanations

    automotive specifications and parts

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

    This neuron detects technical specification details—especially automotive part and fluid identifiers, brand/OEM names, standards (like DOT), and associated numerical measurements and units.

    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
     ihrem
    -1.28
     pels
    -1.25
     вернуться
    -1.20
     their
    -1.20
     haci
    -1.15
     стане
    -1.14
     this
    -1.13
     لا
    -1.13
     partes
    -1.10
     dadas
    -1.09
    POSITIVE LOGITS
     dacă
    1.39
     multicolore
    1.38
     咲
    1.37
     illustratie
    1.30
     such
    1.30
     visse
    1.29
     feltro
    1.29
     băr
    1.28
     quedaron
    1.27
     peintures
    1.25
    Activations Density 0.035%

    No Known Activations