© 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. 69163
    Prev
    Next
    INDEX
    Explanations

    acronyms, abbreviations, symbols

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

    This neuron detects structural or formatting markers in the text—things like bracketed identifiers (e.g. “{#s1-1}”), separator lines, section headings, and similar non-content punctuation/whitespace tokens.

    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
    évolution
    -1.37
    owulf
    -1.32
     beneficios
    -1.28
     irony
    -1.27
    si
    -1.27
    াহ
    -1.27
     jette
    -1.26
     uniquement
    -1.23
     it
    -1.23
    <bos>
    -1.22
    POSITIVE LOGITS
     próprio
    1.31
    隳
    1.30
    地说
    1.29
     Japão
    1.27
    ড
    1.23
    IRQn
    1.22
     name
    1.20
    '
    1.19
     Produtos
    1.18
     deberán
    1.17
    Activations Density 0.192%

    No Known Activations