© 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. 22-GEMMASCOPE-RES-131K
    7. 34001
    Prev
    Next
    INDEX
    Explanations

    market, Notification, Holy Cow

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

    The neuron activates on numeric tokens (years, quantities, and other numbers) 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_22/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
     TikTok
    -2.06
    androidx
    -1.66
     ChatGPT
    -1.61
     covid
    -1.61
     NFTs
    -1.57
     Covid
    -1.50
     COVID
    -1.45
    vermectin
    -1.41
     androidx
    -1.40
    . 
    -1.38
    POSITIVE LOGITS
     http
    1.33
    💁
    1.27
    💓
    1.24
     although
    1.23
    http
    1.23
    💞
    1.19
     Huffington
    1.14
     with
    1.14
    👊
    1.13
     Kinect
    1.12
    Activations Density 0.061%

    No Known Activations