© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 15907
    Prev
    Next
    INDEX
    Explanations

    conditional phrases: if, when, are

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

    The neuron consistently activates on numeric tokens (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
     Livraison
    0.83
     ByteArray
    0.80
    Когда
    0.80
     माझा
    0.79
    𝐽
    0.79
     빛
    0.78
     permitt
    0.77
     이상
    0.77
     cataract
    0.77
     incessantly
    0.77
    POSITIVE LOGITS
    yk
    0.70
    ä
    0.66
    ಾ
    0.66
     وبر
    0.64
    ли
    0.63
     fogl
    0.63
    hmad
    0.62
    っ
    0.61
    ita
    0.60
    ている
    0.60
    Activations Density 0.001%

    No Known Activations