© 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. 92391
    Prev
    Next
    INDEX
    Explanations

    new plus specific phrases

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

    The neuron is primarily triggered by occurrences of the word “New,” especially in titles or proper‐name phrases.

    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
    回忆
    -0.77
     normal
    -0.76
     隔
    -0.75
     дет
    -0.73
     norm
    -0.73
     parame
    -0.72
    satu
    -0.72
    roid
    -0.72
     vod
    -0.71
    żna
    -0.70
    POSITIVE LOGITS
     departure
    0.94
    departure
    0.90
    Departure
    0.81
     departures
    0.80
     viata
    0.80
     яви
    0.79
    vlád
    0.74
     EXPERIMENTAL
    0.74
    laması
    0.74
    arroll
    0.73
    Activations Density 0.042%

    No Known Activations