© 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. 38605
    Prev
    Next
    INDEX
    Explanations

    code block endings

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

    The neuron detects lines of code where a DOM element is being selected or retrieved (e.g. via jQuery’s $() or document.getElementById).

    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
    вій
    -1.00
     beschä
    -0.98
    Suitable
    -0.93
     resident
    -0.93
    </strong>
    -0.91
    </em>
    -0.90
    *
    -0.90
    !
    -0.90
     Page
    -0.88
    3
    -0.87
    POSITIVE LOGITS
     want
    1.23
     wanted
    1.18
     it
    1.16
     cristo
    1.15
     musicale
    1.15
     cortina
    1.13
     pistola
    1.12
     vallen
    1.11
     OBITUARY
    1.09
     Vitória
    1.09
    Activations Density 0.009%

    No Known Activations