© 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. 651
    Prev
    Next
    INDEX
    Explanations

    once again

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

    The neuron highly activates on the adverb “once” (especially in recurring‐emphasis phrases like “once again” or “once more”).

    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
    Organisateur
    -0.94
    デバイス
    -0.89
     広場
    -0.83
     Armada
    -0.81
    をはじめ
    -0.79
    itária
    -0.78
    komme
    -0.78
    跄
    -0.77
     offensi
    -0.77
    ⤻
    -0.77
    POSITIVE LOGITS
     more
    1.44
    more
    1.19
    MORE
    1.18
    More
    1.09
     once
    1.09
     MORE
    1.09
     again
    1.05
     More
    1.00
    Once
    0.89
     más
    0.88
    Activations Density 0.007%

    No Known Activations