© 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. 10599
    Prev
    Next
    INDEX
    Explanations

    math and code structure

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

    The neuron is highly sensitive to standalone punctuation tokens—especially apostrophes, exclamation points, and question marks—marking emphatic or quoted language.

    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
    ر
    0.92
     நீர்
    0.88
     unui
    0.82
     multinational
    0.82
     মানুষের
    0.81
     unei
    0.81
     mondiale
    0.79
     iunie
    0.79
    ঙ্কা
    0.78
    كون
    0.77
    POSITIVE LOGITS
    )?
    0.79
    ){
    0.77
    trl
    0.73
    /)
    0.72
    ланы
    0.72
    orderBy
    0.71
    vá
    0.71
    /}
    0.70
     следует
    0.69
    celebr
    0.69
    Activations Density 0.000%

    No Known Activations