© 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. 64377
    Prev
    Next
    INDEX
    Explanations

    programming system calls and languages

    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
     in
    -2.09
     even
    -1.75
     all
    -1.68
     any
    -1.66
     just
    -1.63
     on
    -1.55
     with
    -1.48
     (
    -1.48
    。　
    -1.39
     had
    -1.38
    POSITIVE LOGITS
    ビックリ
    1.66
     verborgen
    1.57
     aanzien
    1.56
     reveló
    1.55
    為に
    1.55
     permett
    1.52
    ときは
    1.50
     beoor
    1.47
     bewertet
    1.45
    ままで
    1.45
    Activations Density 0.017%

    No Known Activations