© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1296
    Prev
    Next
    INDEX
    Explanations

    list elements, and separators

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

    The neuron reliably activates on standalone numerical tokens (numbers and numeric sequences).

    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
     যাঁরা
    0.50
     সংস্কৃতি
    0.50
    実
    0.50
    ເຂົ້າ
    0.49
     সংস্ক
    0.47
    jár
    0.46
    ㎿
    0.46
     কারখানা
    0.46
    当該
    0.46
    基础设施
    0.45
    POSITIVE LOGITS
    、
    0.68
    ،
    0.59
     、
    0.59
     ,
    0.57
     Surprisingly
    0.57
    ,+
    0.57
    ，
    0.56
     Peptide
    0.56
     Antennes
    0.55
     અને
    0.54
    Activations Density 0.011%

    No Known Activations