© 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. 3831
    Prev
    Next
    INDEX
    Explanations

    with explanations

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

    The main thing this neuron does is detect unusually large decimal numbers or numeric 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_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
    ’
    1.02
    ?
    1.01
    /
    0.94
    ️
    0.89
    <0xD5>
    0.89
    0.86
    "\
    0.85
    i
    0.85
     ​​
    0.85
    ت
    0.85
    POSITIVE LOGITS
    其他
    1.27
    ف
    1.22
    ل
    1.19
    ра
    1.13
    か
    1.11
     العديد
    1.09
     अन्य
    1.09
    अन्य
    1.09
    ح
    1.06
     zahlreiche
    1.04
    Activations Density 0.056%

    No Known Activations