© 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. 127962
    Prev
    Next
    INDEX
    Explanations

    The neuron flags identifier tokens that appear as named parameters in function (or method) signatures.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    function calls and arguments

    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
    Not in Any Lists

    No Comments

    Negative Logits
     your
    -1.17
    neuri
    -1.05
     their
    -1.05
     vuo
    -1.03
     rękaw
    -1.00
     също
    -1.00
     bolsos
    -0.98
    PENDAHULUAN
    -0.98
     sayfası
    -0.97
     its
    -0.96
    POSITIVE LOGITS
    というわけで
    0.98
    并非
    0.89
    邂
    0.89
    Răsp
    0.87
    Regie
    0.87
    コツ
    0.82
    Prensa
    0.82
    vantaged
    0.81
    tools
    0.81
    Оценка
    0.81
    Activations Density 0.008%

    No Known Activations