© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3560
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on snippets of code—especially quoted include statements and PHP file references—i.e. inline code fragments.

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

    page number or section number references in academic citations and bibliographic entries.

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

    bibliographic citation metadata, especially numeric elements like volume/issue notations, page ranges, and other reference formatting in academic-style references.

    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_24_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
     benzyl
    0.80
     Schwarzschild
    0.80
     von
    0.79
    ing
    0.77
    మ్
    0.76
     opioid
    0.76
     bequest
    0.76
     samme
    0.74
    ed
    0.74
     Deacon
    0.73
    POSITIVE LOGITS
    Kindly
    0.98
    Mientras
    0.98
    Namun
    0.96
    Contrary
    0.94
    Однако
    0.89
    Estamos
    0.88
     ພວກເຮົາ
    0.86
    Unfortunately
    0.86
    Knowledge
    0.85
    Якщо
    0.85
    Activations Density 0.001%

    No Known Activations