© 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. 119056
    Prev
    Next
    INDEX
    Explanations

    color combinations and schemes

    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
     avancée
    -0.96
     phénom
    -0.91
     kupić
    -0.90
     étendue
    -0.90
    かわらず
    -0.85
     estilo
    -0.85
    ,$_
    -0.85
     couverte
    -0.85
     style
    -0.85
     colorful
    -0.84
    POSITIVE LOGITS
     scheme
    1.38
     choices
    1.22
     schemes
    1.12
     coordination
    1.07
     choice
    1.05
    blocking
    0.98
     combinations
    0.95
     Scheme
    0.95
     range
    0.93
     theory
    0.93
    Activations Density 0.022%

    No Known Activations