© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12374
    Prev
    Next
    INDEX
    Explanations

    code structure constructs ;

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

    This neuron detects chemical element symbols (e.g. “Fe,” “Ni,” “Co,” “Cu,” etc.) in formulas.

    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_31_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
     Organization
    0.54
     ArrayIndex
    0.52
     ri
    0.52
     kế
    0.52
     ne
    0.51
     Mouse
    0.51
     Organisation
    0.51
     ډ
    0.50
     namesake
    0.50
    ksyon
    0.50
    POSITIVE LOGITS
     сложных
    0.58
     फिल्टर
    0.56
    рав
    0.56
    )\\
    0.55
    徎
    0.55
    ++++++++
    0.54
    लीम
    0.54
    濛
    0.54
    ){//
    0.54
    malt
    0.54
    Activations Density 0.001%

    No Known Activations