© 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. 24-GEMMASCOPE-2-RES-16K
    7. 15282
    Prev
    Next
    INDEX
    Explanations

    lays on its back

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

    The main thing this neuron does is spot numeric expressions and quantitative data (numbers, measurements, statistics, dates).

    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
     হিন্দি
    0.69
    ก
    0.69
     হোল
    0.68
    uacao
    0.67
     validType
    0.66
    יש
    0.66
     twig
    0.65
     יי
    0.65
     comedic
    0.64
     ধর্মীয়
    0.64
    POSITIVE LOGITS
     الموجود
    0.90
    อีก
    0.86
     Minerva
    0.80
    pler
    0.78
    得
    0.77
     Milo
    0.76
    larından
    0.76
    wheels
    0.75
    wounded
    0.75
     Moroz
    0.74
    Activations Density 0.001%

    No Known Activations