© 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. 1
    Prev
    Next
    INDEX
    Explanations

    new product launches and reviews

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

    The neuron fires most strongly on technology/product names and the headline‐style verbs around them (e.g. brand names like “Amazon,” “Xiaomi” and words like “shows,” “review,” “launched,” “pre-order”).

    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
    mgren
    -0.87
     ہیں
    -0.85
    プリング
    -0.83
    analisi
    -0.83
     segnale
    -0.81
     soggetto
    -0.81
     способность
    -0.80
    ⟺
    -0.80
    ėjas
    -0.80
     純正
    -0.79
    POSITIVE LOGITS
     iPhone
    2.81
     Apple
    2.64
    Apple
    2.06
    iPhone
    2.00
     Samsung
    1.96
     iPad
    1.86
     Nintendo
    1.80
     iPhones
    1.79
     Sony
    1.77
     smartphone
    1.77
    Activations Density 0.112%

    No Known Activations