© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 36179
    Prev
    Next
    INDEX
    Explanations

    segments or types

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

    The neuron fires on mentions of fundamental collective communication primitives (e.g. “basic collectives”) in message‐passing library discussions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ガール
    -0.87
     ampere
    -0.87
     Botanical
    -0.83
     heuristic
    -0.83
    UGA
    -0.82
     рабочих
    -0.81
     Pushkin
    -0.81
    おわりに
    -0.81
    NFL
    -0.81
     потенциаль
    -0.79
    POSITIVE LOGITS
     other
    1.00
    其他
    0.94
     других
    0.91
     даже
    0.90
    อื่น
    0.87
     dasarnya
    0.87
    Zunanje
    0.86
     would
    0.85
     perjalanan
    0.85
     没
    0.84
    Activations Density 0.099%

    No Known Activations