© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13093
    Prev
    Next
    INDEX
    Explanations

    function parameter documentation

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

    The neuron specializes in spotting numeric tokens (quantities, measurements, prices, distances, etc.).

    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
    锅
    0.65
    Ꮲ
    0.59
    สดง
    0.59
    oreal
    0.58
    ünd
    0.57
     AOC
    0.57
    샴
    0.57
    eur
    0.55
    不做
    0.53
    קב
    0.52
    POSITIVE LOGITS
    |}
    0.59
     merely
    0.59
    |
    0.57
     수요
    0.56
     アド
    0.53
     ওয়
    0.52
     ジ
    0.51
     سي
    0.50
    打開
    0.49
     التاريخ
    0.49
    Activations Density 0.015%

    No Known Activations