© 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. 6803
    Prev
    Next
    INDEX
    Explanations

    phrases ending with punctuation

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

    The neuron fires on function‐call lines that output or assert string messages (e.g. calls like expect(...), System.out.print(...), alert(...), SOPHUS_TEST_EQUAL(...), etc.).

    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
    deauna
    -2.56
     ciment
    -2.48
    呖
    -2.47
    怍
    -2.44
     ingrained
    -2.39
    ſelves
    -2.38
    𖤣
    -2.36
    捽
    -2.34
    醱
    -2.31
    $
    -2.30
    POSITIVE LOGITS
    y
    4.19
    t
    3.41
    u
    3.09
    in
    2.95
    on
    2.94
    an
    2.84
    {
    2.78
    胧
    2.67
    啬
    2.59
    d
    2.58
    Activations Density 0.001%

    No Known Activations