© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 418
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens—especially four‐digit numbers representing years.

    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
     this
    0.42
    ’
    0.41
     it
    0.40
     that
    0.40
     of
    0.39
     the
    0.36
     
    0.36
     you
    0.36
     have
    0.35
     to
    0.34
    POSITIVE LOGITS
    сійскай
    0.32
    lbrakk
    0.32
    <unused462>
    0.30
    <unused465>
    0.30
    <unused1917>
    0.30
    爣
    0.30
    হইবে
    0.29
    <unused467>
    0.29
     উহার
    0.29
    拡散方程式
    0.29
    Activations Density 3.659%

    No Known Activations