© 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. 127676
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on numeric tokens (sequences of digits), highlighting any standalone numbers in the text.

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

    award-winner

    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
     or
    -1.63
     also
    -1.39
     more
    -1.21
     our
    -1.21
     people
    -1.12
     by
    -1.10
     continual
    -1.05
     classy
    -1.05
     this
    -1.05
     so
    -1.04
    POSITIVE LOGITS
     conster
    1.12
    jugend
    1.08
     inova
    1.05
     strikingly
    1.04
     grosso
    1.01
     aboli
    1.00
     utile
    0.99
     dando
    0.96
     incess
    0.95
    MockMvc
    0.95
    Activations Density 0.074%

    No Known Activations