© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 87116
    Prev
    Next
    INDEX
    Explanations

    constructor parameters and options

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

    The neuron fires on the JavaScript/TypeScript “…” ellipsis token, i.e. spread or rest operator usage.

    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
    HashSet
    -0.88
     συμβ
    -0.82
     estavam
    -0.79
    吻
    -0.79
     siècles
    -0.77
    獪
    -0.77
     unilateral
    -0.77
    дъ
    -0.75
    ```
    -0.73
     aceste
    -0.72
    POSITIVE LOGITS
     {...
    2.23
     Object
    1.91
    {...
    1.73
    Object
    1.72
     {
    1.48
    ({
    1.32
     {
    1.13
     ({
    1.12
     object
    1.11
    object
    1.05
    Activations Density 0.016%

    No Known Activations