© 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. 10-GEMMASCOPE-RES-131K
    7. 58220
    Prev
    Next
    INDEX
    Explanations

    your call, your story

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is triggered by tokens containing digits or punctuation—especially decimal numbers.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     verhind
    -1.58
     verborgen
    -1.45
     verminder
    -1.42
     MINUTE
    -1.37
     UPDATED
    -1.36
     ALERT
    -1.35
     geschenk
    -1.32
     dringend
    -1.32
     PERFECT
    -1.31
     RAJ
    -1.31
    POSITIVE LOGITS
     to
    2.17
     more
    2.03
     any
    1.65
     [
    1.55
     five
    1.52
     It
    1.47
    penup
    1.42
     if
    1.41
     up
    1.41
     infamous
    1.41
    Activations Density 0.011%

    No Known Activations