© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130622
    Prev
    Next
    INDEX
    Explanations

    rRNA gene

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

    The neuron activates for the term "rRNA" (ribosomal RNA) especially when it appears in scientific and biological contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron fires on tokens that look like technical identifiers—words mixing letters with numbers, underscores, or unusual capitalization (e.g. open_rq, rRNA).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anún
    -3.03
     墊
    -2.92
    脔
    -2.77
     北市
    -2.72
     icona
    -2.67
     求人
    -2.59
    It
    -2.58
    ⃚
    -2.55
    𔘓
    -2.53
    They
    -2.52
    POSITIVE LOGITS
     "
    3.03
    翃
    2.84
    …"
    2.81
    𐬹
    2.77
    …’
    2.73
    ¹
    2.52
    ?"
    2.50
     generando
    2.47
    鶿
    2.44
     разных
    2.39
    Activations Density 0.024%

    No Known Activations