© 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. 128264
    Prev
    Next
    INDEX
    Explanations

    The neuron is triggered by numeric tokens—especially multi‐digit numbers such as measurements, years, values, and codes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    month of age; year old

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     before
    -1.24
     requirements
    -1.23
     during
    -1.22
     that
    -1.20
     masukan
    -1.17
     controladores
    -1.16
     methods
    -1.16
     hiasan
    -1.16
     operations
    -1.15
     бампер
    -1.15
    POSITIVE LOGITS
    automne
    1.13
     solen
    1.11
     tuss
    1.08
    Tor
    1.07
     Ecommerce
    1.05
     jil
    1.05
     handcuffs
    1.04
     discer
    1.03
    édition
    1.02
     costar
    1.02
    Activations Density 0.002%

    No Known Activations