© 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. 10-GEMMASCOPE-RES-131K
    7. 13148
    Prev
    Next
    INDEX
    Explanations

    Rx libraries

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

    The neuron activates on the token “Rx” (and variants thereof) whenever ReactiveX–style library or type names appear in code.

    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
    </h3>
    -3.11
    le
    -2.86
    o
    -2.81
    馓
    -2.63
    la
    -2.56
    d
    -2.53
    r
    -2.41
    鲼
    -2.41
    翃
    -2.38
    h
    -2.36
    POSITIVE LOGITS
    Other
    2.86
    沨
    2.50
     Это
    2.47
    》：
    2.44
    𓍊
    2.41
    Three
    2.39
    Five
    2.36
     Because
    2.33
     After
    2.31
    Two
    2.30
    Activations Density 0.003%

    No Known Activations