© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 40826
    Prev
    Next
    INDEX
    Explanations

    closing quotation mark followed by word

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

    The neuron detects stylized opening and closing double-quote characters in text.

    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
    Every
    -2.20
    These
    -2.19
    Each
    -2.16
    Surprisingly
    -2.02
    Both
    -2.00
    This
    -1.99
    Those
    -1.98
    During
    -1.95
    Whether
    -1.93
    That
    -1.90
    POSITIVE LOGITS
    </b>
    2.38
    ↵
    2.20
    g
    2.11
    il
    2.09
     if
    2.05
    of
    2.02
     też
    2.00
    </sup>
    1.91
    w
    1.88
     again
    1.85
    Activations Density 0.009%

    No Known Activations