© 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. 1393
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on the “Answer” label (i.e. the start-of-answer marker in a Q&A format).

    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
     знамена
    0.56
    ถนน
    0.54
     {\
    0.52
     가수
    0.51
    
    0.50
    ilayer
    0.50
    Whis
    0.50
    기준
    0.49
    晾
    0.49
    どのように
    0.49
    POSITIVE LOGITS
    Answer
    0.61
    :][
    0.59
     answer
    0.59
     answered
    0.59
    ansing
    0.59
    answered
    0.57
    answer
    0.56
     pejabat
    0.55
    يف
    0.55
    otheby
    0.54
    Activations Density 0.000%

    No Known Activations