© 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. 22-GEMMASCOPE-RES-131K
    7. 32634
    Prev
    Next
    INDEX
    Explanations

    when the

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    それにしても
    -1.41
    <bos>
    -1.33
     if
    -1.32
    了自己
    -1.30
     nejlepší
    -1.28
     it
    -1.27
     why
    -1.26
     geralmente
    -1.25
     gezicht
    -1.20
    了自己的
    -1.17
    POSITIVE LOGITS
     Within
    1.34
    這些
    1.30
    These
    1.24
     These
    1.22
    撰文
    1.20
    D
    1.20
    中略
    1.19
     этим
    1.18
    Not
    1.16
    んですね
    1.15
    Activations Density 0.041%

    No Known Activations