© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1152
    Prev
    Next
    INDEX
    Explanations

    siRNA interference

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

    RNA interference-related terms and concepts, particularly focusing on siRNA (small interfering RNA).

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

    The neuron is selectively activated by technical mentions of RNA‐mediated gene silencing—especially phrases about suppression of gene expression by double-stranded or small interfering RNAs (RNA interference).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     태
    -0.76
     hist
    -0.75
     excursions
    -0.75
    းက
    -0.74
     churches
    -0.73
     색
    -0.73
     Donations
    -0.73
    JSONException
    -0.72
     posts
    -0.71
     gute
    -0.70
    POSITIVE LOGITS
     siRNA
    1.41
     knockdown
    1.12
     silencing
    0.93
     SMART
    0.90
    interference
    0.89
     sih
    0.89
     interference
    0.87
     esi
    0.85
     knocking
    0.84
    干扰
    0.84
    Activations Density 0.039%

    No Known Activations