© 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. 69979
    Prev
    Next
    INDEX
    Explanations

    was founding or creation

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

    The neuron flags occurrences of the past‐tense copula “was” in factual or historical statements.

    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
     and
    -1.25
    新的
    -1.12
    曾经
    -1.01
    通常
    -1.00
     Händler
    -0.98
    ちゃった
    -0.97
    になるので
    -0.96
    clases
    -0.95
    jadwal
    -0.95
    需要
    -0.93
    POSITIVE LOGITS
    ﾌ
    1.06
    leş
    0.92
    スー
    0.90
    靓
    0.90
    おまけ
    0.89
    デカ
    0.88
     was
    0.88
    umerable
    0.88
    gestellt
    0.87
    对象的
    0.87
    Activations Density 0.179%

    No Known Activations