© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5316
    Prev
    Next
    INDEX
    Explanations

    JSON formatting

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

    The neuron flags numeric literals with decimal points (floating-point 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
     ack
    0.68
    .—
    0.62
     به‌
    0.61
     tende
    0.60
    .#
    0.57
     existentes
    0.57
     hoy
    0.56
     Existing
    0.56
     EVER
    0.56
     schist
    0.55
    POSITIVE LOGITS
    0.58
    Decoration
    0.55
    令
    0.52
    บา
    0.52
    0.52
     ম্যাগ
    0.51
     หล
    0.51
    บาง
    0.51
    Randy
    0.51
    Comparer
    0.50
    Activations Density 0.000%

    No Known Activations