© 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. 9100
    Prev
    Next
    INDEX
    Explanations

    division by

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

    The neuron is triggered by numeric tokens representing quantitative values (especially floating‐point or large numbers).

    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
    International
    0.55
    INTERNATIONAL
    0.54
    ;|&
    0.54
    ጳ
    0.53
    ++++++++++++++++
    0.52
    ણ
    0.52
    ">+
    0.52
    tomorrow
    0.52
    Primer
    0.52
     جيم
    0.52
    POSITIVE LOGITS
     divided
    1.95
     ÷
    1.95
     divide
    1.84
    ÷
    1.81
     dividido
    1.73
     dividir
    1.73
     Divided
    1.70
    divided
    1.70
     Divide
    1.68
    divide
    1.68
    Activations Density 0.089%

    No Known Activations