© 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. 870
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens—especially floating-point or large numerical values—highlighting occurrences of numbers in the text.

    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
    려는
    0.57
    喈
    0.51
    міна
    0.47
    厛
    0.46
    쐞
    0.46
    ="__
    0.45
     characteristic
    0.45
    ϭ
    0.45
    리아
    0.44
    द्व
    0.43
    POSITIVE LOGITS
     trotzdem
    0.54
    ätz
    0.54
     Gets
    0.54
     Anmeldung
    0.53
    ၄
    0.53
     auch
    0.52
    ایک
    0.52
     রেজিস্ট্র
    0.52
    しっかりと
    0.52
     dennoch
    0.51
    Activations Density 0.000%

    No Known Activations