© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71146
    Prev
    Next
    INDEX
    Explanations

    `com` domain and `require` statements

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

    The neuron fires on numeric tokens (digits or digit sequences) embedded in code or technical snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    や
    -0.92
    ïse
    -0.90
     piatta
    -0.89
    bigliamento
    -0.87
    LOO
    -0.87
     Paren
    -0.87
     Tch
    -0.87
     extérieures
    -0.86
     Yap
    -0.86
    störungen
    -0.85
    POSITIVE LOGITS
    ITCHEN
    0.90
     wirklich
    0.82
    (!__
    0.81
    ctools
    0.80
     auge
    0.77
    ==""){
    0.77
    >−</
    0.75
    </h2>
    0.75
     ihren
    0.75
    siębior
    0.74
    Activations Density 0.004%

    No Known Activations