© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 662
    Prev
    Next
    INDEX
    Explanations

    words starting a quote

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

    This neuron detects lines of direct speech—opening quotation marks and the start of spoken dialogue.

    oai_token-act-pair · gpt-5-mini
    Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     logo
    0.27
     fron
    0.26
     taco
    0.26
     server
    0.26
     hardware
    0.25
     features
    0.25
     shimmer
    0.25
     ?.
    0.25
     "+"
    0.25
     visual
    0.25
    POSITIVE LOGITS
    There
    0.52
    People
    0.44
    You
    0.44
    They
    0.43
    The
    0.42
    When
    0.41
    Using
    0.41
    I
    0.41
    It
    0.40
    That
    0.40
    Activations Density 0.051%

    No Known Activations