© 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. 10-GEMMASCOPE-RES-131K
    7. 65093
    Prev
    Next
    INDEX
    Explanations

    default settings and values

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

    The neuron fires on occurrences of the literal token “Default.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    änemark
    -2.89
    犼
    -2.16
     devenu
    -2.06
    ні
    -2.06
     Gegensatz
    -2.05
    plona
    -2.03
    咙
    -2.02
     этапе
    -2.00
    模样
    -1.99
    ations
    -1.98
    POSITIVE LOGITS
    结语
    2.47
    洐
    2.38
    の方は
    2.31
    </sup>
    2.28
    桕
    2.16
    姈
    2.14
    営業時間
    2.13
    la
    2.11
    了一
    2.09
    緜
    2.06
    Activations Density 0.003%

    No Known Activations