© 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. 10-GEMMASCOPE-RES-131K
    4. 105911
    Prev
    Next
    INDEX
    Explanations

    “indexed” type columns

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

    This neuron detects text enclosed in quotation marks—that is, quoted strings or titles.

    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
     This
    -3.25
     Presently
    -3.11
     Utilizing
    -2.98
    The
    -2.94
     Currently
    -2.73
     Concerning
    -2.72
     Practically
    -2.69
    丏
    -2.69
     Whats
    -2.69
     Exactly
    -2.69
    POSITIVE LOGITS
    ,”
    2.91
    퐼
    2.86
    ’
    2.83
    ’.
    2.59
    ました
    2.53
    .’
    2.50
     to
    2.50
    鼍
    2.48
     ему
    2.42
      “
    2.41
    Activations Density 0.023%

    No Known Activations