© 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. 690
    Prev
    Next
    INDEX
    Explanations

    both... and

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

    The neuron strongly responds to coordinating connectors—especially words like “both,” “and,” “including,” “even,” etc.—that link parallel elements in 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
    3
    0.52
    2
    0.48
    4
    0.46
    8
    0.44
     其他
    0.44
    9
    0.44
    6
    0.43
    1
    0.43
    ’
    0.41
    7
    0.41
    POSITIVE LOGITS
     sexes
    0.53
     hinsichtlich
    0.46
     genders
    0.45
     kalo
    0.43
     hemispheres
    0.43
     onshore
    0.41
     novices
    0.41
     sham
    0.40
     pekerjaan
    0.39
     newcomers
    0.39
    Activations Density 0.273%

    No Known Activations