© 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. 59853
    Prev
    Next
    INDEX
    Explanations

    various kinds of notation

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

    This neuron activates on the term “notation” (or its variants) in questions and answers.

    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
    泺
    -2.70
    ﯼ
    -2.67
    唵
    -2.59
    铱
    -2.42
     kopen
    -2.34
    ！"
    -2.31
    殒
    -2.30
    辙
    -2.28
    usnya
    -2.28
    仉
    -2.27
    POSITIVE LOGITS
    n
    2.98
    </sup>
    2.78
    ↵
    2.78
    ”;
    2.56
    </em>
    2.50
    </h4>
    2.50
    the
    2.42
    5
    2.42
    ...
    2.41
    “
    2.33
    Activations Density 0.004%

    No Known Activations