© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11801
    Prev
    Next
    INDEX
    Explanations

    exponentiation with superscripts

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

    The neuron selectively activates on chemical element symbols and stoichiometric formula tokens (e.g., “TiO₂,” “POCl₃,” “H₂O,” etc.).

    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
    }(\
    0.73
     \
    0.71
    $(\
    0.70
     squares
    0.70
    =-\
    0.67
    }\
    0.66
     square
    0.66
    }\{\
    0.66
     massless
    0.65
    =-
    0.64
    POSITIVE LOGITS
    <sup>
    0.84
    ™.
    0.82
     $_{
    0.73
    ®.
    0.73
    ^{-(
    0.71
     $^{
    0.71
    ™,
    0.69
     $^{\
    0.66
    $_{
    0.66
     ${
    0.65
    Activations Density 0.012%

    No Known Activations