© 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. 6680
    Prev
    Next
    INDEX
    Explanations

    apostrophe s

    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
     さま
    -2.48
     帅气
    -2.41
    ).”
    -2.39
    釓
    -2.34
    ......”
    -2.31
    鸰
    -2.23
    chenta
    -2.22
    remadura
    -2.20
    ——”
    -2.19
    縈
    -2.14
    POSITIVE LOGITS
    '
    6.69
     "
    3.67
     '
    3.52
    ,"
    3.50
    ."
    3.30
     ("
    3.14
     "'
    3.02
     ('
    3.00
    /
    2.92
     '"
    2.72
    Activations Density 0.230%

    No Known Activations