© 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. 14957
    Prev
    Next
    INDEX
    Explanations

    The neuron flags tokens representing precise numerical values—especially floating‐point numbers with decimals.

    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
    The
    0.46
     Amherst
    0.44
    an
    0.44
    Clinical
    0.44
     Gastroenter
    0.43
    1
    0.43
     The
    0.42
    d
    0.42
    l
    0.41
     During
    0.41
    POSITIVE LOGITS
     choses
    0.42
     tingkat
    0.42
     crappy
    0.42
     fabriqu
    0.42
     monstru
    0.41
     funcion
    0.41
    ্তির
    0.40
     trabalho
    0.40
     descom
    0.40
     makhluk
    0.40
    Activations Density 0.000%

    No Known Activations