© 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. 10-GEMMASCOPE-RES-131K
    7. 40641
    Prev
    Next
    INDEX
    Explanations

    code, programming, or technical documentation

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

    This neuron activates on code-like tokens and syntax—especially JavaScript/D3 constructs (e.g. “var,” method calls like append, selectAll, path, attr, enter/exit, etc.).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     such
    -1.94
     konsult
    -1.60
     anadolu
    -1.59
     tekno
    -1.55
     elektrik
    -1.53
    膂
    -1.53
     ilyen
    -1.49
    Such
    -1.48
    开发者
    -1.48
    ｃｍ
    -1.48
    POSITIVE LOGITS
     we
    2.02
     мы
    1.52
     Pfar
    1.50
     I
    1.48
     además
    1.46
     today
    1.40
     llamo
    1.38
     finalmente
    1.37
     vuelve
    1.37
     again
    1.35
    Activations Density 0.030%

    No Known Activations