© 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. 34-GEMMASCOPE-RES-131K
    7. 70033
    Prev
    Next
    INDEX
    Explanations

    Volkswagen, TDI, DSG

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

    The neuron activates on numeric tokens—digits and numbers (often in measurements or model specifications).

    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
     tänka
    -0.76
    ların
    -0.75
    ∅
    -0.75
     Chevrolet
    -0.72
     Römer
    -0.71
     BMW
    -0.70
     Ferrari
    -0.69
    ocally
    -0.68
     Υ
    -0.68
     McMahon
    -0.68
    POSITIVE LOGITS
     DSG
    1.58
     VW
    1.48
     Volkswagen
    1.32
     TDI
    1.32
    VW
    1.29
     TSI
    1.27
    Volkswagen
    1.13
     vw
    1.07
     Audi
    1.00
    vw
    0.98
    Activations Density 0.017%

    No Known Activations