© 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. 83770
    Prev
    Next
    INDEX
    Explanations

    measure space, measure theory, measure time

    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
    _
    -2.50
    自己是
    -2.42
    釹
    -2.38
    たまに
    -2.33
    保育園
    -2.31
     measures
    -2.25
    気付
    -2.17
    ization
    -2.13
     singularly
    -2.11
    ৢ
    -2.11
    POSITIVE LOGITS
    ↵
    3.36
    <bos>
    2.70
    ла
    2.20
    It
    2.16
    好了
    2.13
     ‘‘
    2.08
     blanca
    2.08
    然后再
    2.06
    on
    1.99
    ’，
    1.98
    Activations Density 0.010%

    No Known Activations