© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13536
    Prev
    Next
    INDEX
    Explanations

    Piped processing language (PPL)

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

    The neuron fires on four-digit decimal numbers (e.g. “1501.1149”) typical of arXiv paper identifiers or similar numeric references.

    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
    .!
    0.88
     significato
    0.84
     testicule
    0.77
     glande
    0.76
     caule
    0.75
    ي
    0.74
     accomplishing
    0.74
     volontà
    0.73
    ܂
    0.73
     trasferimento
    0.73
    POSITIVE LOGITS
     শিশ
    0.83
    在
    0.79
    邹
    0.75
    ια
    0.72
    lls
    0.71
    rst
    0.70
    ↵
    0.70
    ll
    0.70
    il
    0.70
    对
    0.68
    Activations Density 0.000%

    No Known Activations