© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8840
    Prev
    Next
    INDEX
    Explanations

    electro- prefixes

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

    The neuron fires on numeric tokens containing decimal points (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_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
     אני
    0.64
    我觉得
    0.60
    我覺得
    0.58
     думаю
    0.57
    我认为
    0.56
     jeg
    0.54
    我想
    0.54
     ≈
    0.53
    ἷ
    0.53
     मैं
    0.53
    POSITIVE LOGITS
    격을
    0.56
     इत्यादि
    0.54
     Guide
    0.54
    sob
    0.53
     সৌ
    0.52
     વાળ
    0.52
     álgebra
    0.52
    Abbreviations
    0.52
     انٹر
    0.51
    তত্ব
    0.51
    Activations Density 0.038%

    No Known Activations