© 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. 13402
    Prev
    Next
    INDEX
    Explanations

    before

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

    The neuron identifies numeric tokens containing a decimal point (i.e., floating-point 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_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
    ب
    0.98
    зва
    0.76
    ل
    0.76
     it
    0.71
    িতে
    0.70
     Venn
    0.70
     คร
    0.70
     afield
    0.70
    1
    0.68
    བ
    0.68
    POSITIVE LOGITS
     треба
    0.99
     échanges
    0.93
    ທີ່ຈະ
    0.91
     necesitaba
    0.90
     ruedas
    0.86
     alemán
    0.86
    庀
    0.84
    觎
    0.84
    ни
    0.84
    ாம்
    0.83
    Activations Density 0.003%

    No Known Activations