© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 5139
    Prev
    Next
    INDEX
    Explanations

    function calls and async operations

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

    The neuron primarily detects numeric tokens, especially floating‐point or large numerical measurements.

    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
    Ш
    1.02
    Ж
    0.95
    Ս
    0.94
    к
    0.92
    С
    0.91
    CXX
    0.89
    Java
    0.88
    reference
    0.88
    NULL
    0.87
    я
    0.86
    POSITIVE LOGITS
     useEffect
    0.99
     axios
    0.97
    ()=>{
    0.91
     fintech
    0.91
     DeFi
    0.91
     Kherson
    0.90
     melatonin
    0.88
     dismissing
    0.87
     trafficking
    0.87
     cortisol
    0.87
    Activations Density 0.000%

    No Known Activations