© 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. 8639
    Prev
    Next
    INDEX
    Explanations

    dependency injection and UI outlets

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

    The neuron activates on annotation tokens (the “@…” markers and related framework annotation imports) 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
     l
    -1.34
    &)
    -1.32
     Polym
    -1.29
    ↟
    -1.28
    GraphicsUnit
    -1.27
     currently
    -1.27
    TypedDataSet
    -1.27
     dAtA
    -1.27
    InputBorder
    -1.21
    嵎
    -1.21
    POSITIVE LOGITS
     and
    1.59
     in
    1.41
     jednu
    1.41
    ized
    1.26
     It
    1.25
     innych
    1.22
    autres
    1.22
    }
    1.20
    brought
    1.20
     прежде
    1.20
    Activations Density 0.037%

    No Known Activations