© 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. 24-GEMMASCOPE-2-RES-16K
    7. 15203
    Prev
    Next
    INDEX
    Explanations

    confirming questions

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires strongly on the discourse tag “right?”—i.e. the little rhetorical “right?” at the end of a sentence.

    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
     THEIR
    0.62
     abundantly
    0.54
    attled
    0.51
    0
    0.51
    ਨ
    0.51
     profusely
    0.49
     প্রাণে
    0.49
     nếu
    0.48
    igere
    0.48
     தம்
    0.47
    POSITIVE LOGITS
    ⁈
    0.69
    Arkadaşlar
    0.67
     Zeits
    0.66
    镤
    0.65
    ค่ะ
    0.64
    股份有限公司
    0.61
     Austausch
    0.61
    سي
    0.61
     Vorder
    0.61
     ค่ะ
    0.60
    Activations Density 0.020%

    No Known Activations