© 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. 2350
    Prev
    Next
    INDEX
    Explanations

    the presence of standalone decimal numbers (floating‐point numerical values).

    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
     mert
    0.57
     pero
    0.56
     {
    0.55
     yakni
    0.55
     the
    0.54
     einzelnen
    0.54
     sodass
    0.54
     según
    0.52
     supaya
    0.52
     "./
    0.51
    POSITIVE LOGITS
    は
    0.72
    은
    0.72
     has
    0.66
    は大
    0.65
     đã
    0.62
     ഒരു
    0.62
     была
    0.62
     имеет
    0.61
    是一个
    0.60
    has
    0.59
    Activations Density 0.000%

    No Known Activations