© 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. 22-GEMMASCOPE-RES-131K
    7. 129690
    Prev
    Next
    INDEX
    Explanations

    The neuron detects mentions of programming interfaces or APIs and related technical documentation jargon.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    programming and coding concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    三个
    -1.05
    FlatButton
    -1.00
     otros
    -0.99
    轮胎
    -0.97
    imensional
    -0.97
    暂时
    -0.94
    kinase
    -0.94
    ⬘
    -0.93
    类型
    -0.91
     other
    -0.90
    POSITIVE LOGITS
    omalies
    1.23
    hundreds
    1.22
     alſo
    1.10
    Banyak
    1.09
    thousands
    1.04
     many
    1.03
     produttore
    1.03
    abcdefghijklmnop
    1.00
     poetas
    1.00
     undocumented
    1.00
    Activations Density 0.253%

    No Known Activations