© 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. 72249
    Prev
    Next
    INDEX
    Explanations

    distinctive: followed by a noun

    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
    渽
    -2.78
    你别
    -2.59
    很喜欢
    -2.56
    甞
    -2.47
    獁
    -2.45
    0
    -2.42
    还不错
    -2.41
    簠
    -2.38
    很赞
    -2.34
    不该
    -2.30
    POSITIVE LOGITS
    ’
    4.16
    ist
    3.61
    á
    2.45
    咈
    2.42
    ’，
    2.38
    ia
    2.36
    iy
    2.34
    as
    2.34
    ila
    2.30
     heartfelt
    2.28
    Activations Density 0.002%

    No Known Activations