© 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. 10-GEMMASCOPE-RES-131K
    7. 38385
    Prev
    Next
    INDEX
    Explanations

    endings of text and lists

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

    The neuron detects ellipsis or truncation markers (sequences of dots or dashes indicating “…Continue Reading” or similar).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    There
    -2.48
    As
    -2.34
    Quite
    -2.25
    Several
    -2.25
    Also
    -2.22
    Before
    -2.19
    Some
    -2.17
    Many
    -2.17
    Not
    -2.11
    After
    -2.11
    POSITIVE LOGITS
    饜
    2.63
     Chriſt
    2.53
     luy
    2.33
    齶
    2.33
     THOSE
    2.28
    擡
    2.25
     zwart
    2.23
     hien
    2.20
    矬
    2.17
    mathrm
    2.13
    Activations Density 0.027%

    No Known Activations