© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7867
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily responds to numeric tokens (numeric literals and numbers).

    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
      
    1.28
     부터
    1.21
     সাধারন
    1.09
     ()=>
    1.09
     ঘোষনা
    1.00
     নির্মান
    1.00
     perchè
    0.97
     까지
    0.97
     পৌছ
    0.96
     ऑफ़
    0.96
    POSITIVE LOGITS
    ᄒ
    1.05
    ᅲ
    0.95
    ᄏ
    0.91
    さまざまな
    0.84
     ₹
    0.84
     Afterward
    0.82
     ″
    0.77
    सुद्धा
    0.76
     afterward
    0.76
    〞
    0.74
    Activations Density 0.002%

    No Known Activations