© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5336
    Prev
    Next
    INDEX
    Explanations

    conclusion indicating a result

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

    This neuron selectively activates on numeric tokens or measurements (especially floating-point numbers).

    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
    你在
    0.55
     ½
    0.53
     ¾
    0.51
     spermatozoa
    0.51
     Thirdly
    0.49
     you
    0.48
     electrolytes
    0.47
    你有
    0.46
     chcete
    0.46
     vowels
    0.46
    POSITIVE LOGITS
     உருவாக்கிய
    0.52
    ฒ
    0.51
    现实
    0.49
    developed
    0.49
    色
    0.48
    कल्
    0.47
    とは思
    0.47
    വില്‍
    0.46
    ण्यात
    0.46
    Stub
    0.45
    Activations Density 0.002%

    No Known Activations