© 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. 104985
    Prev
    Next
    INDEX
    Explanations

    initialisms and acronyms

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

    acronyms and abbreviations that consist of capital letters separated by periods.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron detects individual uppercase letters that are part of dot-separated acronyms or initialisms (e.g. M.I.T., H.I.V.E., T.I.D.A., etc.).

    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
    Surprisingly
    -2.17
    Despite
    -2.16
     برای
    -2.11
     unrelenting
    -2.09
    Эти
    -2.06
     для
    -2.05
     Surprisingly
    -2.00
    These
    -1.99
    Almost
    -1.95
    That
    -1.94
    POSITIVE LOGITS
    镲
    2.16
    猡
    2.08
    鱨
    1.98
     realmente
    1.94
    艄
    1.92
    commonly
    1.91
    ౧
    1.90
    姈
    1.88
    \
    1.84
     cinq
    1.84
    Activations Density 0.030%

    No Known Activations