© 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. 10429
    Prev
    Next
    INDEX
    Explanations

    refine, clarify, keep, book, anxiety, data, step, result, features

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

    This neuron detects numeric tokens (numbers and numeric expressions).

    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
    1
    0.77
    2
    0.67
    Е
    0.66
    𝙀
    0.66
     blazing
    0.65
    3
    0.65
    //
    0.64
    同事
    0.63
    Synchron
    0.61
     replicating
    0.61
    POSITIVE LOGITS
     द्
    0.89
     умень
    0.87
     verwendet
    0.85
     прибыль
    0.85
    ளின்
    0.83
    ിയ്
    0.82
     verwenden
    0.79
     vrouwen
    0.79
    ዣ
    0.79
    ȇ
    0.79
    Activations Density 0.004%

    No Known Activations