© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8062
    Prev
    Next
    INDEX
    Explanations

    http or https URLs

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

    The neuron fires primarily on numeric tokens and numeric sequences (e.g. numbers, stats, decimals) 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_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
    」
    0.83
    ）
    0.78
     ）
    0.77
    ುದು
    0.74
    ]
    0.70
     Перейти
    0.68
    0.67
     isa
    0.64
    はお
    0.64
    ವಾಡ
    0.63
    POSITIVE LOGITS
     which
    1.84
    ™.
    1.64
    ®.
    1.58
     nhưng
    1.56
     ซึ่ง
    1.56
    which
    1.54
     :).
    1.54
     които
    1.52
     waardoor
    1.52
     которая
    1.51
    Activations Density 1.503%

    No Known Activations