© 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. 13091
    Prev
    Next
    INDEX
    Explanations

    This neuron primarily detects date and time references (e.g., month names, day or year 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
     nga
    0.73
     despert
    0.69
     avantaj
    0.68
     abges
    0.68
     Miet
    0.68
     funzioni
    0.67
     knapp
    0.65
    搛
    0.65
     madera
    0.64
     Advantages
    0.64
    POSITIVE LOGITS
    おお
    0.66
    Armor
    0.63
    ErrMsg
    0.63
    btnClear
    0.62
    сей
    0.60
    ortal
    0.58
    ících
    0.57
    smanship
    0.56
    Glen
    0.56
    اة
    0.55
    Activations Density 0.318%

    No Known Activations