© 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. 34-GEMMASCOPE-RES-131K
    7. 106323
    Prev
    Next
    INDEX
    Explanations

    drilling assembly or treatment

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     and
    -1.34
     $^{
    -1.34
     stated
    -1.33
    に入れる
    -1.30
     \&
    -1.30
     acorde
    -1.28
    </em>
    -1.28
    に入る
    -1.27
     this
    -1.22
     one
    -1.21
    POSITIVE LOGITS
     เรา
    1.49
     geene
    1.45
    <bos>
    1.45
     inſ
    1.41
     mavi
    1.38
     juſt
    1.37
     captiv
    1.32
     涂
    1.32
     samti
    1.31
     seksi
    1.31
    Activations Density 0.218%

    No Known Activations