© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44474
    Prev
    Next
    INDEX
    Explanations

    siRNA, RNAi types

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

    the prefix "si" in programming, technical, and scientific contexts, especially related to siRNA in biology and domains like GitHub.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    e
    -2.91
    ه
    -2.77
    什么
    -2.64
    in
    -2.50
    as
    -2.36
    istocene
    -2.36
    te
    -2.34
    鄚
    -2.33
    us
    -2.27
     mereka
    -2.25
    POSITIVE LOGITS
    "
    3.16
    vantaged
    2.75
    ’
    2.61
    !"
    2.47
     unor
    2.42
     anguish
    2.41
    /
    2.39
    ?"
    2.36
    ?????
    2.28
     unruly
    2.27
    Activations Density 0.034%

    No Known Activations