© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127797
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to standalone numeric tokens (sequences of digits).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    code-like snippets after delimiters

    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
    Negative Logits
     spesifik
    -1.82
     pantalon
    -1.74
     nacht
    -1.70
     mannen
    -1.66
     decoracion
    -1.64
     vogel
    -1.63
     telefoon
    -1.63
     vorige
    -1.63
     sabun
    -1.57
     reise
    -1.57
    POSITIVE LOGITS
     This
    1.91
          
    1.73
           
    1.70
     D
    1.65
     O
    1.60
     L
    1.59
             
    1.58
         
    1.56
    .....
    1.54
     M
    1.53
    Activations Density 0.000%

    No Known Activations