© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 126
    Prev
    Next
    INDEX
    Explanations

    This neuron specifically fires on the word “Chemistry,” as it appears in academic department or affiliation names.

    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
     financier
    0.57
    এছ
    0.52
     Committee
    0.51
    ל
    0.50
    committee
    0.49
    mış
    0.49
    Committee
    0.49
    government
    0.49
    엊
    0.48
     Confederation
    0.47
    POSITIVE LOGITS
    optosis
    0.59
    ė
    0.57
     and
    0.56
    itton
    0.55
     και
    0.54
    碱
    0.53
    ッシュ
    0.53
    鹼
    0.53
     и
    0.52
    ćen
    0.52
    Activations Density 0.000%

    No Known Activations