© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129631
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on tokens that contain embedded digits (i.e. alphanumeric tokens ending or containing numbers).

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

    observable properties or data structures

    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
     just
    -1.60
     emblema
    -1.52
     all
    -1.39
     epitom
    -1.38
     by
    -1.38
     without
    -1.35
     on
    -1.30
     every
    -1.29
     one
    -1.27
     nestled
    -1.27
    POSITIVE LOGITS
     tradicionales
    1.29
    ̶
    1.27
     trám
    1.24
     amazingly
    1.21
     quirky
    1.20
     EVEN
    1.18
     acclaimed
    1.17
                      
    1.17
     ブラウン
    1.16
     queste
    1.15
    Activations Density 0.003%

    No Known Activations