© 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. 6731
    Prev
    Next
    INDEX
    Explanations

    date, comma, or list item connector

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

    The neuron is keyed to identify numeric tokens (numbers and numeric expressions) in the text.

    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
    ።
    0.75
     кеңсеси
    0.71
    ICIENCY
    0.68
    ;
    0.67
    Collecting
    0.66
    on
    0.66
     نہیں۔
    0.66
    。
    0.66
     ဟ
    0.65
     sĩ
    0.65
    POSITIVE LOGITS
     escuchado
    0.84
    几
    0.76
    ⏯
    0.76
    טים
    0.73
    🌬
    0.73
    httphttps
    0.73
    קים
    0.73
    गर
    0.72
     mantenerse
    0.72
    几个
    0.70
    Activations Density 0.000%

    No Known Activations