© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 98653
    Prev
    Next
    INDEX
    Explanations

    library imports and code blocks

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

    The neuron flags module‐ or library‐name tokens in import/include statements (e.g. resource classes like “R,” utility classes like “Utils,” or header filenames).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     dä
    -0.93
     provocado
    -0.90
    Efter
    -0.90
    ඹ
    -0.89
     to
    -0.89
    𝙲
    -0.88
    dotted
    -0.88
     utveckling
    -0.85
    *}$
    -0.84
    Still
    -0.84
    POSITIVE LOGITS
    wände
    0.91
     Martí
    0.90
    inosi
    0.89
    ragend
    0.86
     menu
    0.85
    請繼續往下閱讀
    0.84
     worin
    0.84
     ಮ
    0.84
    owią
    0.83
    OOTDTY
    0.83
    Activations Density 0.003%

    No Known Activations