© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 6909
    Prev
    Next
    INDEX
    Explanations

    perl `use strict; use warnings;`

    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
    幀
    -0.75
     constituer
    -0.74
     Engle
    -0.73
     raps
    -0.72
    Déf
    -0.71
    yczą
    -0.71
     accéder
    -0.71
     out
    -0.69
     perpetrated
    -0.69
     Ramona
    -0.68
    POSITIVE LOGITS
     lenguaje
    0.88
    麒麟
    0.66
    marca
    0.65
     empirical
    0.64
    Lorenzo
    0.64
    🤙
    0.63
    规范
    0.62
    Updates
    0.62
     Develop
    0.61
     Ernst
    0.61
    Activations Density 0.075%

    No Known Activations