© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32721
    Prev
    Next
    INDEX
    Explanations

    opening quotation marks

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

    The neuron detects the opening of a direct quotation (the initial curly quote mark and start of quoted speech).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    álně
    -1.12
    >\<
    -1.12
     écoulé
    -1.09
     espr
    -1.08
     didn
    -1.05
    Allister
    -1.05
     aulas
    -1.03
    äne
    -1.02
    tôi
    -1.02
     satisfactor
    -1.01
    POSITIVE LOGITS
     we
    1.56
     therefore
    1.33
     infatti
    1.18
     this
    1.15
    ,
    1.10
    indeed
    1.04
     indeed
    1.01
    this
    1.00
    these
    0.98
    挲
    0.92
    Activations Density 0.007%

    No Known Activations