© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15879
    Prev
    Next
    INDEX
    Explanations

    academic assessment and risks

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

    The neuron fires on abstract, nominalized terms (especially those ending in –ion, –ment, –ing, etc.) that commonly appear as method or topic keywords in academic paper titles.

    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
     S
    0.49
     J
    0.47
     M
    0.47
     Vgl
    0.46
    S
    0.45
    K
    0.44
     \{
    0.44
    \{\
    0.43
     Jpn
    0.43
     AcOH
    0.43
    POSITIVE LOGITS
    :
    0.71
     for
    0.63
    ?:
    0.61
    __:
    0.60
    សម្រាប់
    0.59
     для
    0.58
     during
    0.57
     برای
    0.57
    សម្រាប់ការ
    0.57
     জন্য
    0.56
    Activations Density 0.001%

    No Known Activations