© 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. 9443
    Prev
    Next
    INDEX
    Explanations

    with preceding or following certain tokens

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

    The main thing this neuron does is detect numeric tokens (numbers, decimals, phone numbers, data values).

    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
    udio
    0.57
    ▽
    0.54
     মধ্যকার
    0.53
     উল্লেখ
    0.51
    ونا
    0.51
    តម្លៃ
    0.51
    obra
    0.50
    ⋙
    0.50
    added
    0.50
    添加到
    0.50
    POSITIVE LOGITS
     связано
    0.81
     birlikte
    0.79
     জড়িত
    0.74
     karşılaş
    0.74
    有关
    0.71
     связана
    0.71
     தொடர்பு
    0.71
     ساتھ
    0.69
    相比
    0.69
     kapcsolat
    0.69
    Activations Density 0.071%

    No Known Activations