© 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. 34-GEMMASCOPE-RES-131K
    7. 30795
    Prev
    Next
    INDEX
    Explanations

    car types, brands, and colors

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

    This neuron primarily fires on numeric tokens (digits and multi‐digit sequences) and other numeric information in the text.

    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
     atque
    -0.93
    yani
    -0.84
    setAdapter
    -0.84
    iyi
    -0.81
    ItemLayout
    -0.81
    Damit
    -0.80
    这项
    -0.79
    ╞
    -0.79
    Innen
    -0.79
     Automobil
    -0.78
    POSITIVE LOGITS
     vehicle
    1.21
     newer
    1.14
     white
    1.02
     registered
    1.02
     rental
    1.00
     older
    0.97
     hochwertige
    0.93
     gray
    0.91
     suspected
    0.90
     operated
    0.89
    Activations Density 0.023%

    No Known Activations