© 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. 8474
    Prev
    Next
    INDEX
    Explanations

    geometrical deformations, Export Clearance, replication defective

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

    The neuron fires on numeric tokens containing a decimal point (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
    MEM
    0.86
    তথ
    0.83
    땅
    0.80
    銨
    0.79
     использования
    0.76
    при
    0.74
     elems
    0.73
    화
    0.73
    grades
    0.72
     값이
    0.72
    POSITIVE LOGITS
     toer
    0.68
    obao
    0.68
    َّة
    0.67
     enh
    0.67
     justru
    0.67
    ganggu
    0.67
     Kembali
    0.64
    agliari
    0.64
     menit
    0.63
     whilst
    0.63
    Activations Density 0.000%

    No Known Activations