© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10395
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on floating-point numeric tokens (numbers with decimal points).

    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
     και
    0.73
     and
    0.65
     бывшего
    0.63
     и
    0.62
    us
    0.61
     និង
    0.60
     و
    0.59
     và
    0.58
     และ
    0.58
    và
    0.57
    POSITIVE LOGITS
     interstices
    0.65
     embank
    0.57
     există
    0.55
     easements
    0.55
     SLAs
    0.53
     stately
    0.53
     SPMs
    0.52
     COc
    0.52
     Substances
    0.51
     potholes
    0.51
    Activations Density 0.009%

    No Known Activations