© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 2333
    Prev
    Next
    INDEX
    Explanations

    The neuron detects high-frequency English indefinite determiners or pronouns—especially “any” and “other.”

    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
     한다는
    0.82
     꾸
    0.79
     한다
    0.75
     Họ
    0.71
     gestão
    0.70
    uves
    0.70
     성
    0.69
     सम्मिलित
    0.69
     याचिका
    0.69
     ម
    0.68
    POSITIVE LOGITS
    та
    0.89
    י
    0.86
    ड्डी
    0.83
    бр
    0.77
     environ
    0.75
    iak
    0.74
     lugs
    0.73
    ജ്
    0.72
    ا
    0.71
    gek
    0.70
    Activations Density 0.000%

    No Known Activations