© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 11014
    Prev
    Next
    INDEX
    Explanations

    programming keywords and structures

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

    The neuron fires on numeric expressions (counts, measurements, durations, percentages, and other numbers).

    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_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
    [];
    0.54
     Would
    0.54
    :\\
    0.54
    Meaning
    0.53
    ong
    0.52
    Which
    0.52
    adam
    0.52
    Would
    0.52
     JAM
    0.52
     __
    0.51
    POSITIVE LOGITS
     arrayOf
    0.89
     when
    0.87
    arrayOf
    0.85
     когда
    0.84
     quando
    0.83
     cuando
    0.82
     когато
    0.82
     khi
    0.81
     wanneer
    0.79
     listOf
    0.78
    Activations Density 0.004%

    No Known Activations