© 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. 1849
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on numeric tokens and date-like sequences (e.g. day/month/year and other multi-digit expressions).

    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
    abhavena
    1.09
    abhuto
    1.08
    llabus
    1.05
    aparikkh
    1.05
    ॕ
    1.05
     फेस्टिव
    1.05
    alaikums
    1.03
    ruptcy
    1.02
     হোমিওপ্যাথির
    1.02
    iftoire
    1.02
    POSITIVE LOGITS
    <unused61>
    1.09
    ↵↵
    1.05
    <unused62>
    1.00
    ↵
    0.95
    ,
    0.95
    <0xC2>
    0.94
    <unused60>
    0.93
      
    0.89
    <0x0D>
    0.89
     […]
    0.86
    Activations Density 0.856%

    No Known Activations