© 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. 24-GEMMASCOPE-2-RES-16K
    7. 7979
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on past-tense verb forms (e.g. “passed”).

    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_24_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
    AR
    0.88
    no
    0.88
    TE
    0.87
    bal
    0.82
    m
    0.82
    TER
    0.81
    ret
    0.79
    iv
    0.79
    eno
    0.78
    وني
    0.76
    POSITIVE LOGITS
     С
    0.80
    然后
    0.79
    вки
    0.79
     стр
    0.76
    га
    0.75
    而不是
    0.75
    流行
    0.75
     შემდეგ
    0.75
     мебель
    0.74
     Productos
    0.74
    Activations Density 0.000%

    No Known Activations