© 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. 9466
    Prev
    Next
    INDEX
    Explanations

    in relation to

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

    The neuron is specialized in detecting numeric expressions and quantitative data (numbers, statistics, and measurements) 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
    ใน
    1.32
     in
    1.11
     în
    1.09
     в
    1.00
     في
    0.98
     ใน
    0.98
     فى
    0.95
    În
    0.95
    In
    0.91
    in
    0.87
    POSITIVE LOGITS
     regards
    1.16
     accordance
    1.05
     forbindelse
    1.00
     domaines
    0.98
     отношениях
    0.97
     forhold
    0.95
     terms
    0.95
     рамках
    0.91
     oblasti
    0.91
     котором
    0.91
    Activations Density 0.492%

    No Known Activations