© 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. 11986
    Prev
    Next
    INDEX
    Explanations

    `empty` or `async`

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

    The neuron flags occurrences of Android’s text package (e.g. tokens in “android.text.*” imports or API uses).

    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
    CIRCLE
    -0.80
    结局
    -0.69
    ConstraintMaker
    -0.69
     TOXIC
    -0.69
     clay
    -0.69
     wood
    -0.69
     vodou
    -0.69
     botanique
    -0.68
     acontecimientos
    -0.68
     aks
    -0.67
    POSITIVE LOGITS
    isEmpty
    1.29
     isEmpty
    1.20
     empty
    0.93
    IsEmpty
    0.93
     Reduced
    0.81
     앞
    0.79
    Orléans
    0.79
     Empty
    0.79
     مرة
    0.77
    isNameExpr
    0.76
    Activations Density 0.001%

    No Known Activations