© 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. 57036
    Prev
    Next
    INDEX
    Explanations

    database migrations

    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
    9
    -0.72
    飪
    -0.71
     diterima
    -0.70
    вайтесь
    -0.70
    分で
    -0.70
     vinaigrette
    -0.70
     trinken
    -0.69
     rød
    -0.69
    time
    -0.68
     by
    -0.68
    POSITIVE LOGITS
     mig
    1.26
     Migration
    1.11
     Mig
    1.09
     migration
    1.03
    Mig
    1.02
     migra
    1.02
     migrations
    1.01
    migration
    0.99
    Migration
    0.98
    migrate
    0.97
    Activations Density 0.001%

    No Known Activations