© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10910
    Prev
    Next
    INDEX
    Explanations

    `. name` / `. from`

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

    The neuron fires on occurrences of the SVG/CSS “enable‐background” property.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    file paths, URLs, and technical identifiers in code or web development contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    technical programming identifiers and artifacts—CamelCase class/method names, configuration/property keys, and code or URL/module paths, especially from web and Java contexts.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ܬ
    0.41
     Таким
    0.40
    Module
    0.39
    cmd
    0.39
    ਯ
    0.39
    ਟ
    0.39
    ȇ
    0.39
    द्
    0.39
    ཱ
    0.38
    umar
    0.38
    POSITIVE LOGITS
     pesantren
    0.52
     anarchist
    0.49
     cabaret
    0.48
     adherents
    0.46
     BYU
    0.46
     toro
    0.46
     activist
    0.46
     riot
    0.46
     conglomer
    0.45
     gimnas
    0.45
    Activations Density 0.006%

    No Known Activations