© 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. 75002
    Prev
    Next
    INDEX
    Explanations

    `[@B8]` citations

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

    The neuron detects numeric reference markers (the digits in academic citation keys, e.g. the numbers following “B” in “[ @B8]”‐style citations).

    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
    e
    -2.41
    ३
    -1.80
    er
    -1.80
    us
    -1.79
    誊
    -1.77
    al
    -1.75
    In
    -1.70
     usare
    -1.70
    da
    -1.69
    ꜆
    -1.69
    POSITIVE LOGITS
    >
    2.11
     -
    2.06
    \_
    1.97
    푉
    1.86
     '
    1.86
    我只
    1.84
     $
    1.82
     esche
    1.82
    кой
    1.77
     contém
    1.77
    Activations Density 0.019%

    No Known Activations