© 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. 12789
    Prev
    Next
    INDEX
    Explanations

    conditional statements `if`, `with`

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

    The neuron fires on markup tokens—specifically angle-bracketed tags and code-block delimiters.

    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
     Adult
    0.68
     Todes
    0.65
     prue
    0.62
    Adult
    0.62
    ו
    0.62
    Ẩ
    0.61
     А
    0.61
     Ancest
    0.61
    AntiForgery
    0.61
     adulti
    0.60
    POSITIVE LOGITS
    ल्लभ
    0.75
    equations
    0.75
    ጀም
    0.73
     طرق
    0.71
    樎
    0.69
    დან
    0.68
    ጠቀም
    0.68
     ecuaciones
    0.67
     paraphrase
    0.67
     singkat
    0.64
    Activations Density 0.005%

    No Known Activations