© 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. 24-GEMMASCOPE-2-RES-16K
    7. 5551
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on code comments, in particular the “//” comment markers at the start of comment lines.

    oai_token-act-pair · o4-miniTriggered 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
    ly
    0.89
    on
    0.88
    ate
    0.79
    ő
    0.77
    an
    0.77
    ish
    0.76
    man
    0.76
    am
    0.73
    1
    0.73
    ally
    0.71
    POSITIVE LOGITS
     empêcher
    0.75
    इद
    0.73
     حبايبي
    0.71
     milhares
    0.71
     ajust
    0.68
    <unused1972>
    0.68
     adquir
    0.68
     antibiot
    0.67
     obtenir
    0.67
     acquistare
    0.67
    Activations Density 0.000%

    No Known Activations