© 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. 6741
    Prev
    Next
    INDEX
    Explanations

    bind and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    -1.67
     the
    -1.59
    -1.53
    几分
    -1.48
    你现在
    -1.48
     it
    -1.47
    来週
    -1.43
    遊ぶ
    -1.42
    つづく
    -1.41
    にほんブログ村
    -1.40
    POSITIVE LOGITS
     and
    1.78
     浴
    1.45
     واتس
    1.41
    jupe
    1.36
    ELINES
    1.36
    fishing
    1.35
     continúa
    1.31
    除了
    1.30
     uniquement
    1.28
    riy
    1.28
    Activations Density 0.006%

    No Known Activations