© 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. 14684
    Prev
    Next
    INDEX
    Explanations

    list items or enumerated steps

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

    The neuron fires on proper personal names—particularly author names in citation or byline lists.

    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
    इन
    0.71
     is
    0.61
    ወዳ
    0.61
     ស
    0.57
    さは
    0.57
     was
    0.56
    فر
    0.55
    зы
    0.54
    जों
    0.54
    જો
    0.53
    POSITIVE LOGITS
     WHILE
    0.74
    ).*
    0.67
    ☺
    0.66
     .)
    0.66
     (`
    0.65
    🙃
    0.63
     $)$
    0.63
     ขณะ
    0.63
     sambil
    0.62
    ))
    0.61
    Activations Density 0.351%

    No Known Activations