© 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. 56716
    Prev
    Next
    INDEX
    Explanations

    code initialization

    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
    amerikanischer
    -0.93
    teil
    -0.91
     actuellement
    -0.89
    ynie
    -0.85
     actualmente
    -0.85
    harmed
    -0.83
     aident
    -0.83
     plumbers
    -0.81
    ὴ
    -0.81
     actuels
    -0.80
    POSITIVE LOGITS
     variables
    2.08
     necessary
    1.48
     resources
    1.44
     structures
    1.41
     parameters
    1.40
     Variables
    1.36
    variables
    1.34
     environment
    1.33
     with
    1.25
     before
    1.23
    Activations Density 0.030%

    No Known Activations