© 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. 15746
    Prev
    Next
    INDEX
    Explanations

    image links

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

    The neuron is primarily responsive to formatting and markup tokens—backslashes, braces, LaTeX commands, Markdown image syntax, and embedded file‐name numbers—i.e. pieces of code or inline image/link syntax.

    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
    。
    -1.46
    ные
    -1.39
     of
    -1.38
     such
    -1.34
     if
    -1.33
     Aluno
    -1.33
     '
    -1.31
     Spagna
    -1.30
    Diese
    -1.27
     Produto
    -1.26
    POSITIVE LOGITS
    様です
    1.64
     vulgares
    1.53
    Recomendaciones
    1.48
     sposob
    1.46
    uyla
    1.41
    衎
    1.41
    Artículos
    1.41
     perdiendo
    1.38
    れました
    1.36
    ווע
    1.36
    Activations Density 0.007%

    No Known Activations