© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43071
    Prev
    Next
    INDEX
    Explanations

    words in or after quotes

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

    The neuron detects occurrences of the double‐quote character (marks of quoted 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
     evangé
    -2.03
     pérd
    -1.98
     promove
    -1.86
    鸲
    -1.84
    乄
    -1.82
    盉
    -1.78
    鮰
    -1.77
    ፨
    -1.76
     ABOVE
    -1.74
     seules
    -1.73
    POSITIVE LOGITS
     on
    2.16
     out
    1.99
     December
    1.98
     from
    1.96
     for
    1.95
     October
    1.88
     Making
    1.84
     in
    1.81
     Every
    1.77
     and
    1.77
    Activations Density 0.061%

    No Known Activations