© 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. 34-GEMMASCOPE-RES-131K
    7. 3684
    Prev
    Next
    INDEX
    Explanations

    an operator

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

    This neuron fires on uppercase letter sequences—e.g. all-caps words, acronyms, or single-letter mathematical symbols—essentially picking out tokens written entirely in capital letters.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    erli
    -0.76
     Hend
    -0.75
    iferous
    -0.74
    埗
    -0.73
    oude
    -0.73
     bearish
    -0.71
    Ծանոթ
    -0.70
    BOOLEAN
    -0.70
     richer
    -0.69
     индика
    -0.68
    POSITIVE LOGITS
     operators
    2.22
    Operators
    1.88
     operator
    1.85
     Operators
    1.84
    operators
    1.62
    Operator
    1.61
     Operator
    1.53
    operator
    1.46
     operadores
    1.39
     опера
    1.31
    Activations Density 0.055%

    No Known Activations