© 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. 72197
    Prev
    Next
    INDEX
    Explanations

    international lexical items

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

    This neuron marks tokens at the beginnings of sentences.

    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
     such
    -1.75
     noirs
    -1.49
     with
    -1.42
    cisive
    -1.38
    huh
    -1.38
     '*':
    -1.36
     sò
    -1.35
     like
    -1.32
    vertebrate
    -1.32
     comprenant
    -1.30
    POSITIVE LOGITS
     of
    1.79
     uygulama
    1.45
     kişilik
    1.41
    ifdef
    1.37
    raseña
    1.35
    =[]
    1.34
    ですが
    1.34
     mahdollis
    1.30
    ſo
    1.29
     veľa
    1.27
    Activations Density 1.363%

    No Known Activations