© 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. 127647
    Prev
    Next
    INDEX
    Explanations

    This neuron strongly activates on numeric and other non‐alphabetic tokens—e.g. numbers (including decimals and hex), punctuation like apostrophes, and URL/code fragments.

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

    you or your

    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
     inga
    -1.05
     impuls
    -1.05
     jong
    -1.04
     mense
    -1.02
     varier
    -1.02
     coloris
    -0.99
     fuis
    -0.99
     tien
    -0.99
     bains
    -0.99
    aard
    -0.98
    POSITIVE LOGITS
     your
    2.97
     you
    2.69
     You
    1.49
     Your
    1.48
    You
    1.47
    your
    1.45
    Your
    1.40
     YOU
    1.40
     YOUR
    1.38
     yourself
    1.30
    Activations Density 0.020%

    No Known Activations