© 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. 31-GEMMASCOPE-2-RES-16K
    7. 2471
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on numeric tokens (e.g. digits, decimals, or numeric measurements).

    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_31_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
     направлении
    0.64
    🚄
    0.63
     организова
    0.57
    Chiều
    0.57
    Solving
    0.57
    対称
    0.56
    ⊆
    0.56
    achricht
    0.55
    全力
    0.54
     सुमन
    0.54
    POSITIVE LOGITS
    낡
    2.28
     aging
    2.25
     ageing
    2.19
    老化
    2.19
     old
    2.08
     outdated
    2.08
     envej
    2.00
     obsolete
    1.98
     antiquated
    1.97
     vieill
    1.94
    Activations Density 1.194%

    No Known Activations