© 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. 127902
    Prev
    Next
    INDEX
    Explanations

    building, builds, built

    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
     Meksiko
    -1.30
    Komentar
    -1.16
     古风
    -1.12
     作り方
    -1.11
     poë
    -1.08
    Paket
    -1.05
    Energie
    -1.05
    灕
    -1.05
    Namen
    -1.05
     ſch
    -1.05
    POSITIVE LOGITS
    build
    1.61
     build
    1.45
     Build
    1.40
     into
    1.35
     builders
    1.15
     builds
    1.10
    Build
    1.04
    builder
    1.04
     trust
    1.02
     infrastructure
    1.02
    Activations Density 0.073%

    No Known Activations