© 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. 1760
    Prev
    Next
    INDEX
    Explanations

    mathematics and formal proofs

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

    The neuron activates on HTML-style character entity references (e.g. “'”).

    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
     incroyable
    0.97
    成長
    0.95
     youll
    0.92
     sẽ
    0.91
    金額
    0.89
    ⦁
    0.86
    은
    0.84
    ⭐
    0.84
     budete
    0.83
     eCommerce
    0.82
    POSITIVE LOGITS
     automorphisms
    1.11
     algebras
    1.04
     hadrons
    1.04
     manifestly
    1.03
     partition
    1.02
     canonical
    1.02
     inhomogeneities
    1.02
     baryons
    1.02
     simplicial
    1.01
     vbox
    1.00
    Activations Density 0.000%

    No Known Activations