© 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. 91110
    Prev
    Next
    INDEX
    Explanations

    academic results and key outcomes

    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
    minos
    -0.78
    코
    -0.77
    deal
    -0.75
    fl
    -0.74
    Target
    -0.72
    itemize
    -0.72
    righ
    -0.70
     Belly
    -0.69
     manchmal
    -0.69
    сит
    -0.69
    POSITIVE LOGITS
     students
    1.05
     results
    1.00
     résultat
    0.93
     risultato
    0.92
     öğren
    0.89
    电视台
    0.84
     toppers
    0.84
    results
    0.83
     student
    0.82
     schools
    0.82
    Activations Density 0.011%

    No Known Activations