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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28501
    Prev
    Next
    INDEX
    Explanations

    programming examples and code

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

    The neuron detects programming‐code tokens—especially JavaScript and HTML/DOM API terms (e.g. “this,” “document,” “getElementById,” “class,” jQuery selectors, 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_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
     tía
    -1.03
     asse
    -1.01
    最近は
    -0.97
     expédié
    -0.95
     partecipare
    -0.95
     territ
    -0.94
     faç
    -0.94
    wijl
    -0.94
    自分の
    -0.93
    ÄT
    -0.92
    POSITIVE LOGITS
     siente
    1.20
     llevaron
    1.13
     melibatkan
    1.10
     miesięcy
    1.09
     and
    1.08
     родился
    1.08
     ganó
    1.06
     дому
    1.06
     denken
    1.06
    </b>
    1.06
    Activations Density 0.027%

    No Known Activations