© 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. 24-GEMMASCOPE-2-RES-16K
    7. 1663
    Prev
    Next
    INDEX
    Explanations

    hexadecimal constants and numbers

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

    The neuron is detecting numeric tokens representing measurements or statistical values, especially multi‐digit numbers with decimal points.

    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
     proponents
    0.51
    之間的
    0.50
    。
    0.49
    。</
    0.46
     emo
    0.46
    会社
    0.45
    的说
    0.45
    场所
    0.45
    さまざまな
    0.43
    それでは
    0.43
    POSITIVE LOGITS
     ৩
    0.54
     ૩
    0.52
    3
    0.52
    ر
    0.49
     three
    0.48
    e
    0.48
     tři
    0.48
     trois
    0.48
     ১৭
    0.47
     ٣
    0.47
    Activations Density 0.001%

    No Known Activations