© 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. 4328
    Prev
    Next
    INDEX
    Explanations

    numbers followed by descriptive words

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

    The neuron fires on standalone numerals or numeric tokens 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
    人都
    1.02
    𝒈
    1.02
    нит
    0.97
    𝗴
    0.95
     важно
    0.93
    ভাবে
    0.90
    𝒗
    0.89
    𝕄
    0.88
    filenames
    0.88
    чением
    0.88
    POSITIVE LOGITS
    th
    1.32
    ik
    1.29
    -
    1.16
     tenths
    1.06
    as
    1.05
    een
    1.05
    ాన్ని
    1.05
    ️⃣
    1.03
    est
    1.02
    ⃣
    1.02
    Activations Density 3.799%

    No Known Activations