© 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. 8828
    Prev
    Next
    INDEX
    Explanations

    The neuron selectively activates on numerical tokens—especially floating‐point numbers—used for statistical or quantitative data.

    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
    ا
    0.82
     alloying
    0.78
     informatique
    0.78
    واخر
    0.77
    ختار
    0.75
    routingHeader
    0.75
    Ⴊ
    0.75
     nerveux
    0.75
    algèbre
    0.74
     irradi
    0.73
    POSITIVE LOGITS
    st
    1.04
     
    0.98
    TK
    0.96
    dik
    0.92
    n
    0.86
    han
    0.81
     inexperienced
    0.80
    strom
    0.79
    ut
    0.79
    dab
    0.79
    Activations Density 0.000%

    No Known Activations