© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 57985
    Prev
    Next
    INDEX
    Explanations

    pre-order SIGNED Archive Continuous infusion

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

    The neuron is specialized to spot the word “default” (especially in the context of Bazel/Go build rules).

    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
    一群
    -1.56
    urrent
    -1.52
    ———-
    -1.34
    ——–
    -1.34
    .
    -1.33
     Aluno
    -1.33
    li
    -1.31
    your
    -1.30
    gamon
    -1.29
    "}}>
    -1.29
    POSITIVE LOGITS
    Not
    1.51
    この日は
    1.49
    或者
    1.49
    Kelebihan
    1.47
    Secondo
    1.46
     или
    1.45
     夾
    1.45
    鬟
    1.45
     problemet
    1.43
    8
    1.43
    Activations Density 0.000%

    No Known Activations