© 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. 3333
    Prev
    Next
    INDEX
    Explanations

    software build release number

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ródło
    -0.79
    trap
    -0.67
     noodzake
    -0.66
    ربعة
    -0.65
    …~
    -0.62
     vegetales
    -0.61
    ᴿ
    -0.61
     roar
    -0.61
    gbarkeit
    -0.60
     opgenomen
    -0.60
    POSITIVE LOGITS
     build
    5.16
     Build
    4.63
    build
    4.53
    Build
    4.41
     builds
    4.38
     Builds
    3.69
    builds
    3.39
    Builds
    3.31
    BUILD
    3.30
     BUILD
    3.27
    Activations Density 0.118%

    No Known Activations