© 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. 13663
    Prev
    Next
    INDEX
    Explanations

    function definition or code block

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

    The neuron specializes in spotting PHP code snippets—particularly WordPress hook registrations (e.g. add_action) and related function definitions.

    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
     others
    -1.20
     hectáreas
    -1.20
    甚至
    -1.17
     fewer
    -1.16
     ermittelt
    -1.16
     schnelle
    -1.15
     such
    -1.14
     può
    -1.11
     anything
    -1.09
     verarbeitet
    -1.09
    POSITIVE LOGITS
    structing
    1.09
    bliž
    1.08
    ándo
    1.03
     брюки
    1.03
    了一口
    1.02
    kset
    1.02
     Septembre
    0.99
    нову
    0.98
    новый
    0.98
     aparte
    0.98
    Activations Density 0.008%

    No Known Activations