© 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. 58243
    Prev
    Next
    INDEX
    Explanations

    technical documentation sections

    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
    蚰
    -2.23
     >=",
    -2.22
    ᥀
    -2.17
     <=",
    -2.16
     Sébastien
    -2.13
     ڤ
    -2.09
    噲
    -2.08
    䛗
    -2.06
     FÜR
    -2.05
    驁
    -2.05
    POSITIVE LOGITS
     it
    3.22
     the
    2.88
     in
    2.81
     not
    2.80
     With
    2.36
     to
    2.34
     how
    2.30
     these
    2.28
     by
    2.19
     being
    2.19
    Activations Density 0.001%

    No Known Activations