© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193383
    Prev
    Next
    INDEX
    Explanations

    The neuron detects the end of sentences or phrases, often followed by common sentence starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ंपूर्वी
    0.40
     ज़्यादा
    0.39
    ধানা
    0.39
    Geplaatst
    0.39
     বেশ
    0.38
    <unused90>
    0.36
    iboard
    0.36
    ногие
    0.35
    歉
    0.35
    boBox
    0.35
    POSITIVE LOGITS
     unites
    0.46
     silent
    0.40
    官
    0.38
     sides
    0.38
     minds
    0.37
     disturbances
    0.37
     unnoticed
    0.36
     debates
    0.35
     кров
    0.35
     driven
    0.35
    Activations Density 0.002%

    No Known Activations