© 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. 14101
    Prev
    Next
    INDEX
    Explanations

    javascript code snippets

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

    The neuron consistently fires on JavaScript operator and punctuation tokens (e.g., “||”, “=”, “{};”), effectively detecting code-specific symbols.

    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
     sentence
    -0.99
    𝐕
    -0.98
    ر
    -0.97
     out
    -0.96
     should
    -0.94
     ground
    -0.91
     v
    -0.88
     edges
    -0.88
     on
    -0.88
     col
    -0.88
    POSITIVE LOGITS
     diferite
    1.09
     Menor
    1.05
     filmo
    0.99
     الكهرب
    0.98
    視野
    0.97
     insecto
    0.97
     plumes
    0.96
    Leírás
    0.96
    secta
    0.96
     algumas
    0.96
    Activations Density 0.026%

    No Known Activations