© 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. 10417
    Prev
    Next
    INDEX
    Explanations

    folder paths and file names

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

    The neuron activates on tokens representing high-precision decimal numbers (floating-point numerals).

    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
    em
    0.88
    ak
    0.85
    herent
    0.84
    ور
    0.83
     jetzt
    0.82
    ssa
    0.82
    ز
    0.81
    zen
    0.80
     morrer
    0.80
    et
    0.80
    POSITIVE LOGITS
    ETH
    0.75
     unprotected
    0.74
    до
    0.71
    े
    0.71
    ନ
    0.69
    没有什么
    0.68
    不起
    0.68
    奶
    0.67
     contradicting
    0.66
    HEAP
    0.66
    Activations Density 0.000%

    No Known Activations