© 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. 10082
    Prev
    Next
    INDEX
    Explanations

    RNA

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

    The neuron activates on highly technical molecular-biology descriptions—especially phrases describing riboswitches and RNA-based gene-regulation mechanisms.

    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
     Aik
    0.64
     Brushed
    0.64
     Akar
    0.63
     Christy
    0.59
     ब्रश
    0.59
     Peirce
    0.59
     manžel
    0.59
     paiement
    0.58
     irresist
    0.58
     مهر
    0.58
    POSITIVE LOGITS
     RNA
    1.86
    RNA
    1.73
     RNAs
    1.62
    mRNA
    1.42
     ribonucle
    1.41
     tRNA
    1.40
     Nucleic
    1.39
     rRNA
    1.38
     nucleic
    1.38
     mRNA
    1.37
    Activations Density 0.141%

    No Known Activations